Research map / Detection and segmentation / CNN features
You Should Look at All Objects
Zhenchao Jin, Dongdong Yu, Luchuan Song, Zehuan Yuan, Lequan Yu
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 auxiliary losses to FPN-free Faster R-CNN (ablation) | Faster R-CNN ResNet-101 (no FPN) · COCO val2017 | AP: from 39.0% to 39.6% | Improved |
| add auxiliary losses to FPN-based Faster R-CNN (ablation) | Faster R-CNN ResNet-101-FPN · COCO val2017 | AP: from 39.5% to 39.5% | No clear effect |
| add auxiliary losses (summed) (ablation) | RetinaNet ResNet-101-FPN · COCO val2017 | AP_L: 50.4% to 51.2% | Improved |
| add auxiliary losses (summed) (ablation) | Faster R-CNN ResNet-101-FPN · COCO val2017 | AP_L: 51.6% to 52.2% | Improved |
| add auxiliary losses (summed) (ablation) | RetinaNet ResNet-101-FPN · COCO val2017 | AP_S: 21.7 -> 21.2 | Hurt |
| add uncertainty weighting to auxiliary losses (ablation) | RetinaNet ResNet-101-FPN · COCO val2017 | AP_S: 21.2% to 23.3% | Improved |
| add uncertainty weighting to auxiliary losses (ablation) | Faster R-CNN ResNet-101-FPN · COCO val2017 | AP_S: 21.8% to 24.2% | Improved |
| add uncertainty weighting to auxiliary losses (ablation) | RetinaNet ResNet-101-FPN · COCO val2017 | AP: 38.7 -> 40.1 | Improved |
| add feature grouping to FPN (ablation) | RetinaNet ResNet-101 · COCO val2017 | AP: 38.5 -> 40.2 (+1.7%) | Improved |
| add feature grouping to FPN (ablation) | Faster R-CNN ResNet-101 · COCO val2017 | AP: 39.5 -> 40.6 (+1.1%) | Improved |
| increase cascade times of feature grouping from 1x to 3x (ablation) | RetinaNet ResNet-101 · COCO val2017 | AP: 40.2 -> 40.8 -> 41.2 | Improved |
| increase cascade times of feature grouping from 1x to 3x (ablation) | Faster R-CNN ResNet-101 · COCO val2017 | AP: 40.6 -> 41.7 -> 42.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- Sparse R-CNN — Sparse R-CNN: End-to-End Object Detection With Learnable Proposals (CVPR 2021) · better on 1 of 1 shared result
- FreeAnchor — FreeAnchor: Learning to Match Anchors for Visual Object Detection (NeurIPS 2019) · better on 1 of 1 shared result
- FCOS — FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019) · better on 1 of 1 shared result
- Cascade R-CNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · better on 1 of 1 shared result
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · 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
- Feature Pyramid Networks for Object Detection (CVPR 2017 · similarity 0.91)
- M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network (AAAI 2019 · similarity 0.91)
- AugFPN: Improving Multi-Scale Feature Learning for Object Detection (CVPR 2020 · similarity 0.90)
- Construct Effective Geometry Aware Feature Pyramid Network for Multi-Scale Object Detection (AAAI 2022 · similarity 0.90)
- NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (CVPR 2019 · similarity 0.89)
- HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection (AAAI 2025 · 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.
