Research map / Detection and segmentation / CNN features
FCOS: Fully Convolutional One-Stage Object Detection
Zhi Tian, Chunhua Shen, Hao Chen, Tong He
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 center-ness branch (ablation) | FCOS (ResNet-50-FPN) · COCO minival | AP: 33.5 -> 37.1 | Improved |
| compute center-ness from predicted regression vector instead of separate branch (ablation) | FCOS (ResNet-50-FPN) · COCO minival | AP: 33.5 -> 33.5 | No clear effect |
| add FPN multi-level prediction (ablation) | FCOS · COCO train | best possible recall (%): 95.55 -> 98.40 | Improved |
| add FPN multi-level prediction (ablation) | FCOS · COCO minival | ambiguous samples (%): 23.16 -> 7.14 | Improved |
| raise NMS threshold from 0.50 to 0.60 (ablation) | FCOS (P5) · COCO minival | AP: 36.4 -> 36.5 | No clear effect |
| add Group Normalization to heads (ablation) | FCOS (P5, NMS 0.60) · COCO minival | AP: 36.5 -> 37.1 | Improved |
| produce P6/P7 from P5 instead of C5 (ablation) | FCOS · COCO minival | AP: 36.3 -> 36.4 | No clear effect |
| move center-ness branch to regression branch | FCOS · COCO minival | AP: 37.1 -> 37.4 | Improved |
| add center sampling of ground-truth boxes | FCOS · COCO minival | AP: 37.4 -> 38.1 | Improved |
| add GIoU loss | FCOS · COCO minival | AP: 38.1 -> 38.3 | Improved |
| normalize regression targets by FPN strides | FCOS · COCO minival | AP: 38.3 -> 38.6 | Improved |
| use FCOS (no center-ness) in place of anchor RPN | Faster R-CNN RPN · COCO minival | AR100: 44.7 -> 48.0 | Improved |
Later papers that compared with this method
62 later accepted papers report FCOS as a baseline in their results tables; 59 of them report a better number on most of the results they share with it.
- BGHR: Bridging the Gap Between HBox-Supervised and RBox-Supervised Oriented Object Detection via Adaptive Fine-Grained Sample Mining (AAAI 2025 · better on 6 of 6 shared results)
- Comprehensive Multi-Modal Prototypes Are Simple and Effective Classifiers for Vast-Vocabulary Object Detection (AAAI 2025 · better on 1 of 1 shared result)
- RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark (CVPR 2025 · better on 1 of 1 shared result)
- SET: Spectral Enhancement for Tiny Object Detection (CVPR 2025 · better on 1 of 1 shared result)
- Uncertainty-Aware Gradient Stabilization for Small Object Detection (ICCV 2025 · better on 1 of 1 shared result)
- Co-Student: Collaborating Strong and Weak Students for Sparsely Annotated Object Detection (ECCV 2024 · better on 4 of 4 shared results)
- MatchDet: A Collaborative Framework for Image Matching and Object Detection (AAAI 2024 · better on 3 of 3 shared results)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · better on 3 of 3 shared results)
54 more not listed.
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.
- CornerNet — CornerNet: Detecting Objects as Paired Keypoints (ECCV 2018) · 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
- FCOS: A Simple and Strong Anchor-free Object Detector (TPAMI 2020 · similarity 0.98)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.91)
- Learning Rich Features at High-Speed for Single-Shot Object Detection (ICCV 2019 · similarity 0.90)
- NAS-FCOS: Efficient Search for Object Detection Architectures (IJCV 2021 · similarity 0.89)
- Sparse R-CNN: An End-to-End Framework for Object Detection (TPAMI 2023 · similarity 0.89)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (TPAMI 2016 · 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.
