Research map / Detection and segmentation / CNN features
TOOD: Task-Aligned One-Stage Object Detection
Chengjian Feng, Yujie Zhong, Yu Gao, Matthew R. Scott, Weilin Huang
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 T-head instead of the parallel head to FCOS w/ imprv (ablation) | FCOS w/ imprv · COCO minival | AP: 38.6 -> 40.5 | Improved |
| add T-head instead of the parallel head to ATSS (anchor-free) (ablation) | ATSS · COCO minival | AP: 39.2 -> 41.1 | Improved |
| add T-head instead of the parallel head to FoveaBox (ablation) | FoveaBox · COCO minival | AP: 37.3 -> 38.0 | Improved |
| add TAL sample assignment and loss in place of ATSS assignment (parallel head) (ablation) | ATSS · COCO minival | AP: 39.2 -> 40.3 | Improved |
| add TAP to TAL (18 epochs) (ablation) | TAL · COCO minival | AP: 40.9 -> 42.5 | Improved |
| combine T-head with TAL versus ATSS with parallel head (ablation) | ATSS · COCO minival | AP: 39.2 -> 42.5 | Improved |
| vary number of positive anchors m over 5, 9, 13, 17, 21 (ablation) | TOOD · COCO minival | AP: 42.0~42.5 AP | No clear effect |
| increase beta from 2 to 6 at alpha 0.5 (ablation) | TOOD · COCO minival | AP: 42.4 -> 41.7 | Hurt |
| use alpha 1.0 beta 6 rather than alpha 1.5 beta 8 (ablation) | TOOD · COCO minival | AP: 41.5 -> 42.5 | Improved |
| add T-head and TAL to ATSS, reducing redundant boxes after NMS (ablation) | ATSS · COCO minival | redundant boxes: 25,428 -> 15,242 | Improved |
| add T-head and TAL to ATSS, raising task-alignment PCC (ablation) | ATSS · COCO minival | PCC (top-50): 0.408 -> 0.452 | Improved |
| add DCN to TOOD backbone versus ATSS | TOOD · COCO test-dev | AP: 48.3 -> 51.1 | Improved |
Later papers that compared with this method
4 later accepted papers report TOOD as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection (AAAI 2026 · better on 1 of 1 shared result)
- You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection (NeurIPS 2024 · better on 6 of 6 shared results)
- M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors (NeurIPS 2023 · better on 1 of 1 shared result)
- PIDray: A Large-Scale X-ray Benchmark for Real-World Prohibited Item Detection (IJCV 2023 · 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
- Task-Specific Inconsistency Alignment for Domain Adaptive Object Detection (CVPR 2022 · similarity 0.89)
- AlignDet: Aligning Pre-training and Fine-tuning in Object Detection (ICCV 2023 · similarity 0.89)
- Learning Rich Features at High-Speed for Single-Shot Object Detection (ICCV 2019 · similarity 0.88)
- OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features (ECCV 2020 · similarity 0.88)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.86)
- MatchDet: A Collaborative Framework for Image Matching and Object Detection (AAAI 2024 · 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.
