Research map / Detection and segmentation / Weakly supervised detection and segmentation
ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
Qingze He, Fagui Liu, Dengke Zhang, Qingmao Wei, Quan Tang
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 SMFA (soft-masked feature aggregation) (ablation) | ModuSeg baseline · VOC val | mIoU (%): 84.3 -> 84.6 | Improved |
| add SBP (semantic boundary purification) (ablation) | ModuSeg baseline · VOC val | mIoU (%): 84.3 -> 85.2 | Improved |
| add both SBP and SMFA (ablation) | ModuSeg baseline · VOC val | mIoU (%): 84.3 -> 86.3 | Improved |
| add logits-based filtering to feature bank (CorrCLIP, VOC) (ablation) | CorrCLIP · VOC train | mIoU (%): 68.7 -> 78.8 | Improved |
| add logits-based filtering to feature bank (CorrCLIP, COCO) (ablation) | CorrCLIP · COCO train | mIoU (%): 42.5 -> 54.6 | Improved |
| add logits-based filtering to feature bank (Mask Adapter) (ablation) | Mask Adapter · VOC train | mIoU (%): 76.6 -> 82.4 | Improved |
| add logits-based filtering to feature bank (Mask Adapter) (ablation) | Mask Adapter · COCO train | mIoU (%): 55.1 -> 60.2 | Improved |
| use stronger backbone C-RADIOv4 SO400M instead of DINOv2 ViT-B (ablation) | ModuSeg · VOC val | mIoU (%): 82.9 -> 86.3 | Improved |
| use EntitySeg proposals instead of SAM 2 (ablation) | ModuSeg · VOC val | mIoU (%): 82.6 -> 86.3 | Improved |
| use EntitySeg proposals instead of SAM 2 (ablation) | ModuSeg · COCO val | mIoU (%): 54.8 -> 56.7 | Improved |
| apply ModuSeg to CorrCLIP versus direct zero-shot | CorrCLIP · VOC | mIoU (%): 74.8 -> 86.3 | Improved |
| apply ModuSeg to Mask Adapter versus direct zero-shot | Mask Adapter · VOC | mIoU (%): 81.2 -> 86.6 | Improved |
Closest papers by meaning
- Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (CVPR 2018 · similarity 0.90)
- Weakly Supervised Semantic Segmentation with Boundary Exploration (ECCV 2020 · similarity 0.90)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.90)
- Weakly-Supervised Semantic Segmentation via Sub-Category Exploration (CVPR 2020 · similarity 0.90)
- Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation (CVPR 2018 · similarity 0.90)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · 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.
