Research map / Detection and segmentation / Weakly supervised detection and segmentation
Dissimilarity Coefficient Based Weakly Supervised Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 conditional-network self-diversity (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2007 test | mAP: 50.1 -> 52.9 | Helped |
| Add prediction-network self-diversity (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2007 test | mAP: 52.6 -> 52.9 | Helped |
| Add self-diversity to both networks (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2007 test | mAP: 49.5 -> 52.9 | Helped |
| Set localization-loss ratio to λ=0.33 instead of λ=1 (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2007 test | mAP: 52.1% -> 51.6% | Hurt |
| Set localization-loss ratio to λ=3 instead of λ=1 (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2007 test | mAP: 52.1% -> 52.4% | Helped |
| Apply a score threshold of 0.1 (ablation) | Conditional-net samples · PASCAL VOC 2007 test | mAP: 51.4% -> 51.7% | Helped |
| Apply a score threshold of 0.2 (ablation) | Conditional-net samples · PASCAL VOC 2007 test | mAP: 51.4% -> 52.2% | Helped |
| Apply a score threshold of 0.3 (ablation) | Conditional-net samples · PASCAL VOC 2007 test | mAP: 51.4% -> 51.5% | Helped |
| Apply a score threshold of 0.4 (ablation) | Conditional-net samples · PASCAL VOC 2007 test | mAP: 51.4% -> 51.0% | Hurt |
| Apply a score threshold of 0.5 (ablation) | Conditional-net samples · PASCAL VOC 2007 test | mAP: 51.4% -> 50.6% | Hurt |
| Replace Selective Search proposals with RPN proposals (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2007 | mAP: 52.9 -> 50.9 | Hurt |
| Replace Selective Search proposals with RPN proposals (ablation) | Dissimilarity-coefficient detector · PASCAL VOC 2012 | mAP: 49.5 -> 46.1 | Hurt |
Closest papers by meaning
- W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection (CVPR 2018 · similarity 0.88)
- Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection (CVPR 2020 · similarity 0.87)
- Partial Weakly-Supervised Oriented Object Detection (CVPR 2026 · similarity 0.87)
- Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection (ICLR 2023 · similarity 0.87)
- Min-Entropy Latent Model for Weakly Supervised Object Detection (CVPR 2018 · similarity 0.87)
- Relational Matching for Weakly Semi-Supervised Oriented Object Detection (CVPR 2024 · similarity 0.86)
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.