Log in

Relevant bibliographies by topics / Weakly-supervised semantic segmentation / Journal articles

To see the other types of publications on this topic, follow the link: Weakly-supervised semantic segmentation.

Journal articles on the topic 'Weakly-supervised semantic segmentation'

Author: Grafiati

Published: 14 June 2023

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Weakly-supervised semantic segmentation.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Zhang, Yachao, Zonghao Li, Yuan Xie, Yanyun Qu, Cuihua Li, and Tao Mei. "Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 3421–29. http://dx.doi.org/10.1609/aaai.v35i4.16455.

Full text

Abstract:

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotation. Intuitively, weakly supervised training is a direct solution to reduce the labeling costs. However, for weakly supervised large-scale point cloud semantic segmentation, too few annotations will inevitably lead to ineffective learning of network. We propose an effective weakly supervised method containing two components to solve the above problem. Firstly, we construct a pretext task, \textit{i.e.,} point cloud colorization, with a self-supervised training manner to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network. In this way, the representation capability of the weakly supervised network can be improved by knowledge from a heterogeneous task. Besides, to generative pseudo label for unlabeled data, a sparse label propagation mechanism is proposed with the help of generated class prototypes, which is used to measure the classification confidence of unlabeled point. Our method is evaluated on large-scale point cloud datasets with different scenarios including indoor and outdoor. The experimental results show the large gain against existing weakly supervised methods and comparable results to fully supervised methods.

APA, Harvard, Vancouver, ISO, and other styles

2

Chen, Jie, Fen He, Yi Zhang, Geng Sun, and Min Deng. "SPMF-Net: Weakly Supervised Building Segmentation by Combining Superpixel Pooling and Multi-Scale Feature Fusion." Remote Sensing 12, no. 6 (March 24, 2020): 1049. http://dx.doi.org/10.3390/rs12061049.

Full text

Abstract:

The lack of pixel-level labeling limits the practicality of deep learning-based building semantic segmentation. Weakly supervised semantic segmentation based on image-level labeling results in incomplete object regions and missing boundary information. This paper proposes a weakly supervised semantic segmentation method for building detection. The proposed method takes the image-level label as supervision information in a classification network that combines superpixel pooling and multi-scale feature fusion structures. The main advantage of the proposed strategy is its ability to improve the intactness and boundary accuracy of a detected building. Our method achieves impressive results on two 2D semantic labeling datasets, which outperform some competing weakly supervised methods and are close to the result of the fully supervised method.

APA, Harvard, Vancouver, ISO, and other styles

3

Li, Xueyi, Tianfei Zhou, Jianwu Li, Yi Zhou, and Zhaoxiang Zhang. "Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 3 (May 18, 2021): 1984–92. http://dx.doi.org/10.1609/aaai.v35i3.16294.

Full text

Abstract:

Acquiring sufficient ground-truth supervision to train deep vi- sual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmen- tation, which requires pixel-level annotations. This work ad- dresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level anno- tations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models se- mantic dependencies in a group of images to estimate more reliable pseudo ground-truths, which can be used for training more accurate segmentation models. In particular, we devise a graph neural network (GNN) for group-wise semantic min- ing, wherein input images are represented as graph nodes, and the underlying relations between a pair of images are char- acterized by an efficient co-attention mechanism. Moreover, in order to prevent the model from paying excessive atten- tion to common semantics only, we further propose a graph dropout layer, encouraging the model to learn more accurate and complete object responses. The whole network is end-to- end trainable by iterative message passing, which propagates interaction cues over the images to progressively improve the performance. We conduct experiments on the popular PAS- CAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. Our code is available at: https://github.com/Lixy1997/Group-WSSS.

APA, Harvard, Vancouver, ISO, and other styles

4

Cheng, Hao, Chaochen Gu, and Kaijie Wu. "Weakly-Supervised Semantic Segmentation via Self-training." Journal of Physics: Conference Series 1487 (March 2020): 012001. http://dx.doi.org/10.1088/1742-6596/1487/1/012001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Ouassit, Youssef, Soufiane Ardchir, Mohammed Yassine El Ghoumari, and Mohamed Azouazi. "A Brief Survey on Weakly Supervised Semantic Segmentation." International Journal of Online and Biomedical Engineering (iJOE) 18, no. 10 (July 26, 2022): 83–113. http://dx.doi.org/10.3991/ijoe.v18i10.31531.

Full text

Abstract:

Semantic Segmentation is the process of assigning a label to every pixel in the image that share same semantic properties and stays a challenging task in computer vision. In recent years, and due to the large availability of training data the performance of semantic segmentation has been greatly improved by using deep learning techniques. A large number of novel methods have been proposed. However, in some crucial fields we can't assure sufficient data to learn a deep model and achieves high accuracy. This paper aims to provide a brief survey of research efforts on deep-learning-based semantic segmentation methods on limited labeled data and focus our survey on weakly-supervised methods. This survey is expected to familiarize readers with the progress and challenges of weakly supervised semantic segmentation research in the deep learning era and present several valuable growing research points in this field.

APA, Harvard, Vancouver, ISO, and other styles

6

Kim, Beomyoung, Sangeun Han, and Junmo Kim. "Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (May 18, 2021): 1754–61. http://dx.doi.org/10.1609/aaai.v35i2.16269.

Full text

Abstract:

Weakly-supervised semantic segmentation (WSSS) using image-level labels has recently attracted much attention for reducing annotation costs. Existing WSSS methods utilize localization maps from the classification network to generate pseudo segmentation labels. However, since localization maps obtained from the classifier focus only on sparse discriminative object regions, it is difficult to generate high-quality segmentation labels. To address this issue, we introduce discriminative region suppression (DRS) module that is a simple yet effective method to expand object activation regions. DRS suppresses the attention on discriminative regions and spreads it to adjacent non-discriminative regions, generating dense localization maps. DRS requires few or no additional parameters and can be plugged into any network. Furthermore, we introduce an additional learning strategy to give a self-enhancement of localization maps, named localization map refinement learning. Benefiting from this refinement learning, localization maps are refined and enhanced by recovering some missing parts or removing noise itself. Due to its simplicity and effectiveness, our approach achieves mIoU 71.4% on the PASCAL VOC 2012 segmentation benchmark using only image-level labels. Extensive experiments demonstrate the effectiveness of our approach.

APA, Harvard, Vancouver, ISO, and other styles

7

Zhou, Tianfei, Liulei Li, Xueyi Li, Chun-Mei Feng, Jianwu Li, and Ling Shao. "Group-Wise Learning for Weakly Supervised Semantic Segmentation." IEEE Transactions on Image Processing 31 (2022): 799–811. http://dx.doi.org/10.1109/tip.2021.3132834.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Li, Yi, Yanqing Guo, Yueying Kao, and Ran He. "Image Piece Learning for Weakly Supervised Semantic Segmentation." IEEE Transactions on Systems, Man, and Cybernetics: Systems 47, no. 4 (April 2017): 648–59. http://dx.doi.org/10.1109/tsmc.2016.2623683.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Xiong, Changzhen, and Hui Zhi. "Multi-model Integrated Weakly Supervised Semantic Segmentation Method." Journal of Computer-Aided Design & Computer Graphics 31, no. 5 (2019): 800. http://dx.doi.org/10.3724/sp.j.1089.2019.17379.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Wang, Shuo, and Yizhou Wang. "Weakly Supervised Semantic Segmentation with a Multiscale Model." IEEE Signal Processing Letters 22, no. 3 (March 2015): 308–12. http://dx.doi.org/10.1109/lsp.2014.2358562.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Wang, Xiang, Sifei Liu, Huimin Ma, and Ming-Hsuan Yang. "Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning." International Journal of Computer Vision 128, no. 6 (January 30, 2020): 1736–49. http://dx.doi.org/10.1007/s11263-020-01293-3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Zhou, Ruixue, Zhiqiang Yuan, Xuee Rong, Weicong Ma, Xian Sun, Kun Fu, and Wenkai Zhang. "Weakly Supervised Semantic Segmentation in Aerial Imagery via Cross-Image Semantic Mining." Remote Sensing 15, no. 4 (February 10, 2023): 986. http://dx.doi.org/10.3390/rs15040986.

Full text

Abstract:

Weakly Supervised Semantic Segmentation (WSSS) with only image-level labels reduces the annotation burden and has been rapidly developed in recent years. However, current mainstream methods only employ a single image’s information to localize the target and do not account for the relationships across images. When faced with Remote Sensing (RS) images, limited to complex backgrounds and multiple categories, it is challenging to locate and differentiate between the categories of targets. As opposed to previous methods that mostly focused on single-image information, we propose CISM, a novel cross-image semantic mining WSSS framework. CISM explores cross-image semantics in multi-category RS scenes for the first time with two novel loss functions: the Common Semantic Mining (CSM) loss and the Non-common Semantic Contrastive (NSC) loss. In particular, prototype vectors and the Prototype Interactive Enhancement (PIE) module were employed to capture semantic similarity and differences across images. To overcome category confusions and closely related background interferences, we integrated the Single-Label Secondary Classification (SLSC) task and the corresponding single-label loss into our framework. Furthermore, a Multi-Category Sample Generation (MCSG) strategy was devised to balance the distribution of samples among various categories and drastically increase the diversity of images. The above designs facilitated the generation of more accurate and higher-granularity Class Activation Maps (CAMs) for each category of targets. Our approach is superior to the RS dataset based on extensive experiments and is the first WSSS framework to explore cross-image semantics in multi-category RS scenes and obtain cutting-edge state-of-the-art results on the iSAID dataset by only using image-level labels. Experiments on the PASCAL VOC2012 dataset also demonstrated the effectiveness and competitiveness of the algorithm, which pushes the mean Intersection-Over-Union (mIoU) to 67.3% and 68.5% on the validation and test sets of PASCAL VOC2012, respectively.

APA, Harvard, Vancouver, ISO, and other styles

13

Xu, Xinying, Guiqing Li, Gang Xie, Jinchang Ren, and Xinlin Xie. "Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions." Complexity 2019 (March 14, 2019): 1–12. http://dx.doi.org/10.1155/2019/9180391.

Full text

Abstract:

The task of semantic segmentation is to obtain strong pixel-level annotations for each pixel in the image. For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel-level annotations. However, the pixel-level annotation process is very expensive and time-consuming. To reduce the cost, the paper proposes a semantic candidate regions trained extreme learning machine (ELM) method with image-level labels to achieve pixel-level labels mapping. In this work, the paper casts the pixel mapping problem into a candidate region semantic inference problem. Specifically, after segmenting each image into a set of superpixels, superpixels are automatically combined to achieve segmentation of candidate region according to the number of image-level labels. Semantic inference of candidate regions is realized based on the relationship and neighborhood rough set associated with semantic labels. Finally, the paper trains the ELM using the candidate regions of the inferred labels to classify the test candidate regions. The experiment is verified on the MSRC dataset and PASCAL VOC 2012, which are popularly used in semantic segmentation. The experimental results show that the proposed method outperforms several state-of-the-art approaches for deep semantic segmentation.

APA, Harvard, Vancouver, ISO, and other styles

14

Shen, Fengli, Zhe-Ming Lu, Ziqian Lu, and Zonghui Wang. "Dual semantic-guided model for weakly-supervised zero-shot semantic segmentation." Multimedia Tools and Applications 81, no. 4 (December 22, 2021): 5443–58. http://dx.doi.org/10.1007/s11042-021-11792-1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Wan, Weitao, Jiansheng Chen, Ming-Hsuan Yang, and Huimin Ma. "Co-attention dictionary network for weakly-supervised semantic segmentation." Neurocomputing 486 (May 2022): 272–85. http://dx.doi.org/10.1016/j.neucom.2021.11.046.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Cao, Zhiyuan, Yufei Gao, and Jiacai Zhang. "Scale-aware attention network for weakly supervised semantic segmentation." Neurocomputing 492 (July 2022): 34–49. http://dx.doi.org/10.1016/j.neucom.2022.04.006.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Xu, Lian, Hao Xue, Mohammed Bennamoun, Farid Boussaid, and Ferdous Sohel. "Atrous convolutional feature network for weakly supervised semantic segmentation." Neurocomputing 421 (January 2021): 115–26. http://dx.doi.org/10.1016/j.neucom.2020.09.045.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Xu, Yajun, Zhendong Mao, Zhineng Chen, Xin Wen, and Yangyang Li. "Context propagation embedding network for weakly supervised semantic segmentation." Multimedia Tools and Applications 79, no. 45-46 (March 30, 2020): 33925–42. http://dx.doi.org/10.1007/s11042-020-08787-9.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Xu, Lian, Mohammed Bennamoun, Farid Boussaid, and Ferdous Sohel. "Scale-Aware Feature Network for Weakly Supervised Semantic Segmentation." IEEE Access 8 (2020): 75957–67. http://dx.doi.org/10.1109/access.2020.2989331.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Zhang, Tianyi, Guosheng Lin, Jianfei Cai, Tong Shen, Chunhua Shen, and Alex C. Kot. "Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation." IEEE Transactions on Multimedia 21, no. 11 (November 2019): 2930–41. http://dx.doi.org/10.1109/tmm.2019.2914870.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Shen, Fengli, Zong-Hui Wang, and Zhe-Ming Lu. "Weakly supervised classification model for zero-shot semantic segmentation." Electronics Letters 56, no. 23 (November 12, 2020): 1247–50. http://dx.doi.org/10.1049/el.2020.2270.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Feng, Jiapei, Xinggang Wang, Te Li, Shanshan Ji, and Wenyu Liu. "Weakly-supervised semantic segmentation via online pseudo-mask correcting." Pattern Recognition Letters 165 (January 2023): 33–38. http://dx.doi.org/10.1016/j.patrec.2022.11.024.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Liu, Yang, Zechao Li, Jing Liu, and Hanqing Lu. "Boosted MIML method for weakly-supervised image semantic segmentation." Multimedia Tools and Applications 74, no. 2 (May 9, 2014): 543–59. http://dx.doi.org/10.1007/s11042-014-1967-5.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Fan, Junsong, Zhaoxiang Zhang, Tieniu Tan, Chunfeng Song, and Jun Xiao. "CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 10762–69. http://dx.doi.org/10.1609/aaai.v34i07.6705.

Full text

Abstract:

Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplementary representations can be propagated to obtain more consistent and integral regions. To leverage this information, we propose an end-to-end cross-image affinity module, which exploits pixel-level cross-image relationships with only image-level labels. By means of this, our approach achieves 64.3% and 65.3% mIoU on Pascal VOC 2012 validation and test set respectively, which is a new state-of-the-art result by only using image-level labels for weakly supervised semantic segmentation, demonstrating the superiority of our approach.

APA, Harvard, Vancouver, ISO, and other styles

25

Jiang, Quanchun, Olamide Timothy Tawose, Songwen Pei, Xiaodong Chen, Linhua Jiang, Jiayao Wang, and Dongfang Zhao. "Weakly-Supervised Image Semantic Segmentation Based on Superpixel Region Merging." Big Data and Cognitive Computing 3, no. 2 (June 10, 2019): 31. http://dx.doi.org/10.3390/bdcc3020031.

Full text

Abstract:

In this paper, we propose a semantic segmentation method based on superpixel region merging and convolutional neural network (CNN), referred to as regional merging neural network (RMNN). Image annotation has always been an important role in weakly-supervised semantic segmentation. Most methods use manual labeling. In this paper, super-pixels with similar features are combined using the relationship between each pixel after super-pixel segmentation to form a plurality of super-pixel blocks. Rough predictions are generated by the fully convolutional networks (FCN) so that certain super-pixel blocks will be labeled. We perceive and find other positive areas in an iterative way through the marked areas. This reduces the feature extraction vector and reduces the data dimension due to super-pixels. The algorithm not only uses superpixel merging to narrow down the target’s range but also compensates for the lack of weakly-supervised semantic segmentation at the pixel level. In the training of the network, we use the method of region merging to improve the accuracy of contour recognition. Our extensive experiments demonstrated the effectiveness of the proposed method with the PASCAL VOC 2012 dataset. In particular, evaluation results show that the mean intersection over union (mIoU) score of our method reaches as high as 44.6%. Because the cavity convolution is in the pooled downsampling operation, it does not degrade the network’s receptive field, thereby ensuring the accuracy of image semantic segmentation. The findings of this work thus open the door to leveraging the dilated convolution to improve the recognition accuracy of small objects.

APA, Harvard, Vancouver, ISO, and other styles

26

Moghalles, Khaled, Heng-Chao Li, and Abdulwahab Alazeb. "Weakly Supervised Building Semantic Segmentation Based on Spot-Seeds and Refinement Process." Entropy 24, no. 5 (May 23, 2022): 741. http://dx.doi.org/10.3390/e24050741.

Full text

Abstract:

Automatic building semantic segmentation is the most critical and relevant task in several geospatial applications. Methods based on convolutional neural networks (CNNs) are mainly used in current building segmentation. The requirement of huge pixel-level labels is a significant obstacle to achieve the semantic segmentation of building by CNNs. In this paper, we propose a novel weakly supervised framework for building segmentation, which generates high-quality pixel-level annotations and optimizes the segmentation network. A superpixel segmentation algorithm can predict a boundary map for training images. Then, Superpixels-CRF built on the superpixel regions is guided by spot seeds to propagate information from spot seeds to unlabeled regions, resulting in high-quality pixel-level annotations. Using these high-quality pixel-level annotations, we can train a more robust segmentation network and predict segmentation maps. To iteratively optimize the segmentation network, the predicted segmentation maps are refined, and the segmentation network are retrained. Comparative experiments demonstrate that the proposed segmentation framework achieves a marked improvement in the building’s segmentation quality while reducing human labeling efforts.

APA, Harvard, Vancouver, ISO, and other styles

27

Zhou, Yongxiu, Honghui Wang, Ronghao Yang, Guangle Yao, Qiang Xu, and Xiaojuan Zhang. "A Novel Weakly Supervised Remote Sensing Landslide Semantic Segmentation Method: Combing CAM and cycleGAN Algorithms." Remote Sensing 14, no. 15 (July 29, 2022): 3650. http://dx.doi.org/10.3390/rs14153650.

Full text

Abstract:

With the development of deep learning algorithms, more and more deep learning algorithms are being applied to remote sensing image classification, detection, and semantic segmentation. The landslide semantic segmentation of a remote sensing image based on deep learning mainly uses supervised learning, the accuracy of which depends on a large number of training data and high-quality data annotation. At this stage, high-quality data annotation often requires the investment of significant human effort. Therefore, the high cost of remote sensing landslide image data annotation greatly restricts the development of a landslide semantic segmentation algorithm. Aiming to resolve the problem of the high labeling cost of landslide semantic segmentation with a supervised learning method, we proposed a remote sensing landslide semantic segmentation with weakly supervised learning method combing class activation maps (CAMs) and cycle generative adversarial network (cycleGAN). In this method, we used the image level annotation data to replace pixel level annotation data as the training data. Firstly, the CAM method was used to determine the approximate position of the landslide area. Then, the cycleGAN method was used to generate the fake image without a landslide, and to make the difference with the real image to obtain the accurate segmentation of the landslide area. Finally, the pixel-level segmentation of the landslide area on remote sensing image was realized. We used mean intersection-over-union (mIOU) to evaluate the proposed method, and compared it with the method based on CAM, whose mIOU was 0.157, and we obtain better result with mIOU 0.237 on the same test dataset. Furthermore, we made a comparative experiment using the supervised learning method of a u-net network, and the mIOU result was 0.408. The experimental results show that it is feasible to realize landslide semantic segmentation in a remote sensing image by using weakly supervised learning. This method can greatly reduce the workload of data annotation.

APA, Harvard, Vancouver, ISO, and other styles

28

Lu, Zheng, and Dali Chen. "Weakly Supervised and Semi-Supervised Semantic Segmentation for Optic Disc of Fundus Image." Symmetry 12, no. 1 (January 10, 2020): 145. http://dx.doi.org/10.3390/sym12010145.

Full text

Abstract:

Weakly supervised and semi-supervised semantic segmentation has been widely used in the field of computer vision. Since it does not require groundtruth or it only needs a small number of groundtruths for training. Recently, some works use pseudo groundtruths which are generated by a classified network to train the model, however, this method is not suitable for medical image segmentation. To tackle this challenging problem, we use the GrabCut method to generate the pseudo groundtruths in this paper, and then we train the network based on a modified U-net model with the generated pseudo groundtruths, finally we utilize a small amount of groundtruths to fine tune the model. Extensive experiments on the challenging RIM-ONE and DRISHTI-GS benchmarks strongly demonstrate the effectiveness of our algorithm. We obtain state-of-art results on RIM-ONE and DRISHTI-GS databases.

APA, Harvard, Vancouver, ISO, and other styles

29

Qin, Jie, Jie Wu, Xuefeng Xiao, Lujun Li, and Xingang Wang. "Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 2117–25. http://dx.doi.org/10.1609/aaai.v36i2.20108.

Full text

Abstract:

Image-level weakly supervised semantic segmentation (WSSS) is a fundamental yet challenging computer vision task facilitating scene understanding and automatic driving. Most existing methods resort to classification-based Class Activation Maps (CAMs) to play as the initial pseudo labels, which tend to focus on the discriminative image regions and lack customized characteristics for the segmentation task. To alleviate this issue, we propose a novel activation modulation and recalibration (AMR) scheme, which leverages a spotlight branch and a compensation branch to obtain weighted CAMs that can provide recalibration supervision and task-specific concepts. Specifically, an attention modulation module (AMM) is employed to rearrange the distribution of feature importance from the channel-spatial sequential perspective, which helps to explicitly model channel-wise interdependencies and spatial encodings to adaptively modulate segmentation-oriented activation responses. Furthermore, we introduce a cross pseudo supervision for dual branches, which can be regarded as a semantic similar regularization to mutually refine two branches. Extensive experiments show that AMR establishes a new state-of-the-art performance on the PASCAL VOC 2012 dataset, surpassing not only current methods trained with the image-level of supervision but also some methods relying on stronger supervision, such as saliency label. Experiments also reveal that our scheme is plug-and-play and can be incorporated with other approaches to boost their performance. Our code is available at: https://github.com/jieqin-ai/AMR.

APA, Harvard, Vancouver, ISO, and other styles

30

Colin, Aurélien, Ronan Fablet, Pierre Tandeo, Romain Husson, Charles Peureux, Nicolas Longépé, and Alexis Mouche. "Semantic Segmentation of Metoceanic Processes Using SAR Observations and Deep Learning." Remote Sensing 14, no. 4 (February 11, 2022): 851. http://dx.doi.org/10.3390/rs14040851.

Full text

Abstract:

Through the Synthetic Aperture Radar (SAR) embarked on the satellites Sentinel-1A and Sentinel-1B of the Copernicus program, a large quantity of observations is routinely acquired over the oceans. A wide range of features from both oceanic (e.g., biological slicks, icebergs, etc.) and meteorologic origin (e.g., rain cells, wind streaks, etc.) are distinguishable on these acquisitions. This paper studies the semantic segmentation of ten metoceanic processes either in the context of a large quantity of image-level groundtruths (i.e., weakly-supervised framework) or of scarce pixel-level groundtruths (i.e., fully-supervised framework). Our main result is that a fully-supervised model outperforms any tested weakly-supervised algorithm. Adding more segmentation examples in the training set would further increase the precision of the predictions. Trained on 20 × 20 km imagettes acquired from the WV acquisition mode of the Sentinel-1 mission, the model is shown to generalize, under some assumptions, to wide-swath SAR data, which further extents its application domain to coastal areas.

APA, Harvard, Vancouver, ISO, and other styles

31

Luo, Wenfeng, Meng Yang, and Weishi Zheng. "Weakly-supervised semantic segmentation with saliency and incremental supervision updating." Pattern Recognition 115 (July 2021): 107858. http://dx.doi.org/10.1016/j.patcog.2021.107858.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Vilar, Daniel R., and Claudio A. Perez. "Extracting Structured Supervision From Captions for Weakly Supervised Semantic Segmentation." IEEE Access 9 (2021): 65702–20. http://dx.doi.org/10.1109/access.2021.3076074.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Yoon, SuHyun, and Jee-Hyong Lee. "Weakly-supervised Semantic Segmentation using Pseudo-labels of unlabeled data." Journal of Korean Institute of Intelligent Systems 32, no. 4 (August 31, 2022): 269–74. http://dx.doi.org/10.5391/jkiis.2022.32.4.269.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

HE, Zifen, Shouye ZHU, Ying HUANG, and Yinhui ZHANG. "GECNN for Weakly Supervised Semantic Segmentation of 3D Point Clouds." IEICE Transactions on Information and Systems E104.D, no. 12 (December 1, 2021): 2237–43. http://dx.doi.org/10.1587/transinf.2021edp7134.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Zhe, ZHANG, WANG Bilin, YU Zhezhou, and LI Zhiyuan. "Dilated Convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation." Chinese Journal of Electronics 30, no. 6 (November 2021): 1120–30. http://dx.doi.org/10.1049/cje.2021.08.007.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Kim, Sangtae, Luong Trung Nguyen, Kyuhong Shim, Junhan Kim, and Byonghyo Shim. "Pseudo-Label-Free Weakly Supervised Semantic Segmentation Using Image Masking." IEEE Access 10 (2022): 19401–11. http://dx.doi.org/10.1109/access.2022.3149587.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Lin, Yaping, George Vosselman, and Michael Ying Yang. "Weakly supervised semantic segmentation of airborne laser scanning point clouds." ISPRS Journal of Photogrammetry and Remote Sensing 187 (May 2022): 79–100. http://dx.doi.org/10.1016/j.isprsjprs.2022.03.001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Saleh, Fatemeh Sadat, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez, and Stephen Gould. "Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation." IEEE Transactions on Pattern Analysis and Machine Intelligence 40, no. 6 (June 1, 2018): 1382–96. http://dx.doi.org/10.1109/tpami.2017.2713785.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Shimoda, Wataru, and Keiji Yanai. "Weakly supervised semantic segmentation using distinct class specific saliency maps." Computer Vision and Image Understanding 191 (February 2020): 102712. http://dx.doi.org/10.1016/j.cviu.2018.08.006.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Sun, Wanchun, Xin Feng, and Jingyao Liu. "Non-bias self-attention learning for weakly supervised semantic segmentation." Computers and Electrical Engineering 105 (January 2023): 108496. http://dx.doi.org/10.1016/j.compeleceng.2022.108496.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Dong, Zhiming, Jiajun Wang, Bo Cui, Dong Wang, and Xiaoling Wang. "Patch-based weakly supervised semantic segmentation network for crack detection." Construction and Building Materials 258 (October 2020): 120291. http://dx.doi.org/10.1016/j.conbuildmat.2020.120291.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Awan, Mehwish, and Jitae Shin. "Weakly supervised multi-class semantic video segmentation for road scenes." Computer Vision and Image Understanding 230 (April 2023): 103664. http://dx.doi.org/10.1016/j.cviu.2023.103664.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Al-Huda, Zaid, Bo Peng, Yan Yang, Riyadh Nazar Ali Algburi, Muqeet Ahmad, Faisal Khurshid, and Khaled Moghalles. "Weakly supervised semantic segmentation by iteratively refining optimal segmentation with deep cues guidance." Neural Computing and Applications 33, no. 15 (January 18, 2021): 9035–60. http://dx.doi.org/10.1007/s00521-020-05669-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Dobshik, A. V., A. A. Tulupov, and V. B. Berikov. "Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke." Journal of Physics: Conference Series 2099, no. 1 (November 1, 2021): 012021. http://dx.doi.org/10.1088/1742-6596/2099/1/012021.

Full text

Abstract:

Abstract This paper presents an automatic algorithm for the segmentation of areas affected by an acute stroke in the non-contrast computed tomography brain images. The proposed algorithm is designed for learning in a weakly supervised scenario when some images are labeled accurately, and some images are labeled inaccurately. Wrong labels appear as a result of inaccuracy made by a radiologist in the process of manual annotation of computed tomography images. We propose methods for solving the segmentation problem in the case of inaccurately labeled training data. We use the U-Net neural network architecture with several modifications. Experiments on real computed tomography scans show that the proposed methods increase the segmentation accuracy.

APA, Harvard, Vancouver, ISO, and other styles

45

Al-Huda, Zaid, Donghai Zhai, Yan Yang, and Riyadh Nazar Ali Algburi. "Optimal Scale of Hierarchical Image Segmentation with Scribbles Guidance for Weakly Supervised Semantic Segmentation." International Journal of Pattern Recognition and Artificial Intelligence 35, no. 10 (May 21, 2021): 2154026. http://dx.doi.org/10.1142/s0218001421540264.

Full text

Abstract:

Deep convolutional neural networks (DCNNs) trained on the pixel-level annotated images have achieved improvements in semantic segmentation. Due to the high cost of labeling training data, their applications may have great limitation. However, weakly supervised segmentation approaches can significantly reduce human labeling efforts. In this paper, we introduce a new framework to generate high-quality initial pixel-level annotations. By using a hierarchical image segmentation algorithm to predict the boundary map, we select the optimal scale of high-quality hierarchies. In the initialization step, scribble annotations and the saliency map are combined to construct a graphic model over the optimal scale segmentation. By solving the minimal cut problem, it can spread information from scribbles to unmarked regions. In the training process, the segmentation network is trained by using the initial pixel-level annotations. To iteratively optimize the segmentation, we use a graphical model to refine segmentation masks and retrain the segmentation network to get more precise pixel-level annotations. The experimental results on Pascal VOC 2012 dataset demonstrate that the proposed framework outperforms most of weakly supervised semantic segmentation methods and achieves the state-of-the-art performance, which is [Formula: see text] mIoU.

APA, Harvard, Vancouver, ISO, and other styles

46

Wang, P., and W. Yao. "EXPLORING LABEL INITIALIZATION FOR WEAKLY SUPERVISED ALS POINT CLOUD SEMANTIC SEGMENTATION." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-2-2022 (May 17, 2022): 151–58. http://dx.doi.org/10.5194/isprs-annals-v-2-2022-151-2022.

Full text

Abstract:

Abstract. Although a number of emerging point-cloud semantic segmentation methods achieve state-of-the-art results, acquiring fully interpreted training data is a time-consuming and labor-intensive task. To reduce the burden of data annotation in training, semiand weakly supervised methods are proposed to address the situation of limited supervisory sources, achieving competitive results compared to full supervision schemes. However, given a fixed budget, the effective annotation of a few points is typically ignored, which is referred to as weak-label initialization in this study. In practice, random selection is typically adopted by default. Because weakly supervised methods largely rely on semantic information supplied by initial weak labels, this studies explores the influence of different weak-label initialization strategies. In addition to random initialization, we propose a feature-constrained framework to guide the selection of initial weak labels. A feature space of point clouds is first constructed by feature extraction and embedding. Then, we develop a density-biased strategy to annotate points by locating highly dense clustered regions, as significant information distinguishing semantic classes is often concentrated in such areas. Our method outperforms random initialization on ISPRS Vaihingen 3D data when only using sparse weak labels, achieving an overall accuracy of 78.06% using 1‰ of labels. However, only a minor increase is observed on the LASDU dataset. Additionally, the results show that initialization with category-wise uniformly distributed weak labels is more effective when incorporated using a weakly supervised method.

APA, Harvard, Vancouver, ISO, and other styles

47

Xiao, Junsheng, Huahu Xu, Honghao Gao, Minjie Bian, and Yang Li. "A Weakly Supervised Semantic Segmentation Network by Aggregating Seed Cues: The Multi-Object Proposal Generation Perspective." ACM Transactions on Multimedia Computing, Communications, and Applications 17, no. 1s (March 31, 2021): 1–19. http://dx.doi.org/10.1145/3419842.

Full text

Abstract:

Weakly supervised semantic segmentation under image-level annotations is effectiveness for real-world applications. The small and sparse discriminative regions obtained from an image classification network that are typically used as the important initial location of semantic segmentation also form the bottleneck. Although deep convolutional neural networks (DCNNs) have exhibited promising performances for single-label image classification tasks, images of the real-world usually contain multiple categories, which is still an open problem. So, the problem of obtaining high-confidence discriminative regions from multi-label classification networks remains unsolved. To solve this problem, this article proposes an innovative three-step framework within the perspective of multi-object proposal generation. First, an image is divided into candidate boxes using the object proposal method. The candidate boxes are sent to a single-classification network to obtain the discriminative regions. Second, the discriminative regions are aggregated to obtain a high-confidence seed map. Third, the seed cues grow on the feature maps of high-level semantics produced by a backbone segmentation network. Experiments are carried out on the PASCAL VOC 2012 dataset to verify the effectiveness of our approach, which is shown to outperform other baseline image segmentation methods.

APA, Harvard, Vancouver, ISO, and other styles

48

Shao, Qiqi, Lingjuan Yu, Yuting Guo, Xiaochun Xie, Jianping Zou, and Liang Li. "Weakly Supervised Semantic Segmentation of PolSAR Image Based on Improved SEAM." Journal of Physics: Conference Series 2456, no. 1 (March 1, 2023): 012003. http://dx.doi.org/10.1088/1742-6596/2456/1/012003.

Full text

Abstract:

Abstract Weakly supervised semantic segmentation (WSSS) has been widely studied in optical image field. Self-supervised equivariant attention mechanism (SEAM) effectively improves the WSSS results with the image-level labels. However, when it is directly used in the WSSS of polarimetric synthetic aperture radar (PolSAR) image, the performance is very poor. In this paper, an improved SEAM (ISEAM) is proposed for WSSS of PolSAR image, which uses the improved ResNet as the backbone network. The improvement mainly includes two aspects. First, the structure of ResNet is lightweight, which aims to match the characteristics of PolSAR dataset. Second, a squeeze-and-extraction (SE) attention mechanism is added into the backbone network, which aims to obtain channel-wise information. Experiments on Flevoland and San Francisco datasets show that the proposed ISEAM can achieve better performance than the original SEAM.

APA, Harvard, Vancouver, ISO, and other styles

49

Li, Xi, Huimin Ma, Sheng Yi, Yanxian Chen, and Hongbing Ma. "Single annotated pixel based weakly supervised semantic segmentation under driving scenes." Pattern Recognition 116 (August 2021): 107979. http://dx.doi.org/10.1016/j.patcog.2021.107979.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Wang, Puzuo, and Wei Yao. "A new weakly supervised approach for ALS point cloud semantic segmentation." ISPRS Journal of Photogrammetry and Remote Sensing 188 (June 2022): 237–54. http://dx.doi.org/10.1016/j.isprsjprs.2022.04.016.

Full text

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!