mlsanityData to 14 Oct 2026

Small Objects Matters in Weakly-supervised Semantic Segmentation

arXiv 2309.14117 ↗First posted 25 Sep 2023cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five years. Still, current WSSS literature misses the detailed sense of how well the methods perform on different sizes of objects. Thus we propose a novel evaluation metric to provide a comprehensive assessment across different object sizes and collect a size-balanced evaluation set to complement PASCAL VOC. With these two gadgets, we reveal that the existing WSSS methods struggle in capturing small objects. Furthermore, we propose a size-balanced cross-entropy loss coupled with a proper training strategy. It generally improves existing WSSS methods as validated upon ten baselines on three different datasets.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

37 of 56 references.

References · 37

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  6. 2016Pyramid Scene Parsing Networkcited by 2,479
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  9. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  10. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  11. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 247
  12. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
25 more
  1. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  2. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 227
  3. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  4. 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
  5. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  6. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 188
  7. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 169
  8. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  9. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  10. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  11. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  12. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  13. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
  14. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 98
  15. 2018Self-Erasing Network for Integral Object Attentioncited by 95
  16. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  17. 2019Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approachcited by 88
  18. 2018CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentationcited by 80
  19. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
  20. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  21. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  22. 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
  23. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  24. 2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
  25. 2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Automatic Intermodal Loading Unit Identification using Computer Vision: A Scoping Reviewcited by 0