Research map / Detection and segmentation / Open-set and few-shot detection
CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection
Jiajin Tang, Ge Zheng, Jingyi Yu, Sibei Yang
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 |
|---|---|---|---|
| use affordance-level visual knowledge instead of object categories only (ablation) | CoTDet · COCO-Tasks | mAP_box: 31.9 -> 48.1 | Improved |
| generate visual features per retrieved object instead of one direct query (ablation) | CoTDet · COCO-Tasks | mAP_box: 48.1 -> 52.4 | Improved |
| add rationales to MLCoT (ablation) | CoTDet · COCO-Tasks | mAP_box: 52.4 -> 56.9 | Improved |
| add rationales to MLCoT (ablation) | CoTDet · COCO-Tasks | mAP_mask: 49.0 -> 53.6 | Improved |
| use ChatGPT instead of GPT-3 for knowledge (ablation) | CoTDet · COCO-Tasks | mAP_box: 56.9 -> 57.0 | No clear effect |
| use knowledge to initialize queries instead of Def+TOIST text queries (ablation) | Deformable-DETR · COCO-Tasks | mAP_box: 40.3 -> 48.7 | Improved |
| fuse knowledge with the visual feature map (ablation) | Init w/ MLCoT · COCO-Tasks | mAP_box: 48.7 -> 50.6 | Improved |
| knowledge-conditional query generation (select) instead of fusion (ablation) | Fuse w/ MLCoT · COCO-Tasks | mAP_box: 50.6 -> 55.3 | Improved |
| add knowledge-conditional denoising training (ablation) | CoTDet · COCO-Tasks | mAP_box: 55.3 -> 56.9 | Improved |
| add knowledge-conditional denoising training (ablation) | CoTDet · COCO-Tasks | mAP_mask: 51.7 -> 53.6 | Improved |
| replace TOIST text-initialized queries with full CoTDet decoder (ablation) | Def+TOIST · COCO-Tasks | mAP_box: 40.3 -> 56.9 | Improved |
| replace GGNN/TOIST baselines with CoTDet | TOIST · COCO-Tasks detection | mAP_box: 41.3 -> 56.9 | 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.
- TOIST — TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation (NeurIPS 2022) · better on 4 of 4 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
- One-Shot Object Affordance Detection in the Wild (IJCV 2022 · similarity 0.88)
- DoGA: Enhancing Grounded Object Detection via Grouped Pre-Training with Attributes (AAAI 2025 · similarity 0.86)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds (ICLR 2025 · similarity 0.86)
- Interpreting Object-level Foundation Models via Visual Precision Search (CVPR 2025 · similarity 0.86)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.85)
- Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors (ICLR 2025 · similarity 0.85)
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.
