Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly Supervised Semantic Segmentation with Boundary Exploration
Liyi Chen, Weiwei Wu, Chenchen Fu, Xiao Han, Yuntao Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add boundary exploration (BENet-constrained propagation) (ablation) | attention-pooling CAM · PASCAL VOC 2012 train (pseudo labels) | mIoU: 50.4% to 66.4% | Improved |
| add attention-pooling CAM instead of GAP CAM (ablation) | CAM · PASCAL VOC 2012 train (pseudo labels) | mIoU: 49.6% to 50.4% | Improved |
| add attention pooling on top of boundary exploration (ablation) | CAM + boundary exploration · PASCAL VOC 2012 train (pseudo labels) | mIoU: 65.7 -> 66.4 | Improved |
| add dCRF post-processing of pseudo labels (ablation) | BES · PASCAL VOC 2012 train (pseudo labels) | mIoU: 66.4% to 67.2% | Improved |
| vary theta_diff and theta_scale in boundary label synthesis (ablation) | BES · PASCAL VOC 2012 train (pseudo labels) | mIoU: 65.0 to 66.4 across grid | No clear effect |
| increase attention intensity k beyond a small value (ablation) | attention-pooling CAM · PASCAL VOC 2012 train (pseudo labels) | mIoU | Hurt |
| small attention intensity k versus GAP-based CAM (ablation) | attention-pooling CAM · PASCAL VOC 2012 train (pseudo labels) | mIoU | Improved |
| use BES labels to train DeepLab-ASPP instead of IRNet labels | DeepLab-ASPP · PASCAL VOC 2012 val | mIoU: 63.5 -> 65.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FickleNet — FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference (CVPR 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.92)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.92)
- Weakly-Supervised Semantic Segmentation via Sub-Category Exploration (CVPR 2020 · similarity 0.91)
- Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach (AAAI 2020 · similarity 0.91)
- Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation (CVPR 2021 · similarity 0.91)
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation (CVPR 2017 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
