Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly Supervised Referring Image Segmentation with Intra-Chunk and Inter-Chunk Consistency
Jungbeom Lee, Sungjin Lee, Jinseok Nam, Seunghak Yu, Jaeyoung Do, Tara Taghavi
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 intra-chunk and inter-chunk consistency losses (ablation) | ALBEF Grad-CAM · RefCOCO+ val | mIoU: 22.44 -> 25.68 | Improved |
| add patch-affinity refinement from ViT self-attention (ablation) | ALBEF with chunk consistency · RefCOCO+ val | mIoU: 25.68 -> 29.58 | Improved |
| add MCG unsupervised shape prior (ablation) | ALBEF with chunk consistency and affinity · RefCOCO+ val | mIoU: 29.58 -> 31.28 | Improved |
| add MCG shape prior (ablation) | Ours · RefCOCO+ val | Pr@70: 1.83 -> 9.72 | Improved |
| add intra-chunk and inter-chunk consistency (ablation) | ALBEF · RefCOCO+ val | Pr@50 and Pr@70: Pr@70 0.20 -> 0.34 | No clear effect |
| use layer 10 instead of layer 9 for patch affinity (ablation) | affinity refinement · RefCOCO+ val | mIoU: 29.58 -> 20.71 | Hurt |
| exclude negative captions from intra/inter-chunk losses (ablation) | Ours · RefCOCO+ val | mIoU: 25.68 -> 25.76 | No clear effect |
| add box supervision loss via BBAM pseudo mask | Ours · G-Ref val | oIoU: 46.03 -> 49.64 vs Feng et al. | Improved |
| add chunk consistency to ALBEF for inclusive relation captions | ALBEF · RefCOCO+ val subset, inclusive | mIoU: 24.46 -> 28.72 | Improved |
| add chunk consistency to ALBEF for exclusive relation captions | ALBEF · RefCOCO+ val subset, exclusive | mIoU: 19.62 -> 23.57 | 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.
- GroupViT — GroupViT: Semantic Segmentation Emerges From Text Supervision (CVPR 2022) · 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
- Shatter and Gather: Learning Referring Image Segmentation with Text Supervision (ICCV 2023 · similarity 0.94)
- Boosting Weakly Supervised Referring Image Segmentation via Progressive Comprehension (NeurIPS 2024 · similarity 0.93)
- Referring Image Segmentation Using Text Supervision (ICCV 2023 · similarity 0.93)
- Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation (CVPR 2024 · similarity 0.90)
- Mask Grounding for Referring Image Segmentation (CVPR 2024 · similarity 0.89)
- IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis (AAAI 2025 · similarity 0.89)
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.
