Research map / Detection and segmentation / Weakly supervised detection and segmentation
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Guolei Sun, Wenguan Wang, Jifeng Dai, Luc Van Gool
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 co-attention (common semantics) loss (ablation) | basic classifier · PASCAL VOC12 val | mIoU: 61.7 -> 65.5 | Improved |
| add contrastive co-attention loss (ablation) | co-attention classifier · PASCAL VOC12 val | mIoU: 65.5 -> 66.2 | Improved |
| train with co-attention and contrastive co-attention (single-round inference) (ablation) | basic classifier · PASCAL VOC12 val | mIoU: 61.7 -> 64.7 | Improved |
| use multi-round co-attentive inference with related images (ablation) | co-attention classifier · PASCAL VOC12 val | mIoU: 64.7 -> 66.2 | Improved |
| use contrastive co-attention in localization map inference (ablation) | full model · PASCAL VOC12 val | mIoU: 66.2 -> 66.2 | No clear effect |
| increase related images from 0 to 3 (ablation) | co-attention inference · PASCAL VOC12 val | mIoU: 64.7 -> 66.2 | Improved |
| increase related images from 3 to 4 (ablation) | co-attention inference · PASCAL VOC12 val | mIoU: 66.2 -> 66.1 | Hurt |
| increase related images from 3 to 5 (ablation) | co-attention inference · PASCAL VOC12 val | mIoU: 66.2 -> 66.0 | Hurt |
| use ResNet instead of VGG backbone | Ours · PASCAL VOC12 val (VOC only) | mIoU: 63.5 -> 66.2 | Improved |
| add extra single-label images | Ours (ResNet) · PASCAL VOC12 val | mIoU: 66.2 -> 67.1 | Improved |
| add extra web images | Ours (ResNet) · PASCAL VOC12 val | mIoU: 66.2 -> 67.7 | Improved |
| use co-attention method instead of AttnBN with extra single-label data | AttnBN · PASCAL VOC12 (extra single-label images) val | mIoU: 62.1 -> 67.1 | 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 1 of 1 shared result
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
- Looking Beyond Single Images for Weakly Supervised Semantic Segmentation Learning (TPAMI 2022 · similarity 0.98)
- Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation (TPAMI 2022 · similarity 0.93)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.92)
- Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation (CVPR 2022 · similarity 0.91)
- CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation (CVPR 2022 · similarity 0.91)
- Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (CVPR 2018 · 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.
