Research map / Detection and segmentation / CNN features
Hierarchical Context Embedding for Region-based Object Detection
Zhao-Min Chen, Xin Jin, Borui Zhao, Xiu-Shen Wei, Yanwen Guo
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 image-level multi-label learning (MLL) (ablation) | FPN · COCO 2017 val (ResNet-50-FPN) | AP: 36.3 -> 36.8 | Improved |
| add instance-level context embedding on top of MLL (ablation) | FPN · COCO 2017 val (ResNet-50-FPN) | AP: 36.8 -> 37.8 | Improved |
| add global-level context embedding (ablation) | FPN · COCO 2017 val (ResNet-50-FPN) | AP: 37.8 -> 38.4 | Improved |
| add feature fusion in training (ablation) | FPN with MLL · COCO 2017 val (ResNet-50-FPN) | AP: 36.8 -> 37.6 | Improved |
| add confidence fusion in training (ablation) | FPN with MLL · COCO 2017 val (ResNet-50-FPN) | AP: 36.8 -> 37.4 | Improved |
| train with both fusions instead of feature fusion only (ablation) | FPN with MLL · COCO 2017 val (ResNet-50-FPN) | AP: 37.6 -> 38.4 | Improved |
| test with both branches instead of feature fusion branch only (ablation) | HCE FPN · COCO 2017 val (ResNet-50-FPN) | AP: 38.2 -> 38.4 | No clear effect |
| use feature fusion branch at inference vs baseline (ablation) | HCE FPN · COCO 2017 val (ResNet-50-FPN) | AP: 36.3 -> 38.2 | Improved |
| add HCE to FPN | FPN · COCO 2017 val (ResNet-50-FPN) | AP: 36.3 -> 38.4 | Improved |
| add HCE to FPN | FPN · COCO 2017 val (ResNet-101-FPN) | AP: 38.3 -> 40.0 | Improved |
| add HCE to Mask R-CNN | Mask R-CNN · COCO 2017 val (ResNet-50-FPN) | AP: 37.3 -> 38.8 | Improved |
| add HCE to Cascade R-CNN | Cascade R-CNN · COCO 2017 val (ResNet-50-FPN) | AP: 40.5 -> 41.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Cascade R-CNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · better on 3 of 3 shared results
- FCOS — FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019) · 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
- Transformer-Based Context Condensation for Boosting Feature Pyramids in Object Detection (IJCV 2023 · similarity 0.90)
- ContextShift: A Controlled Benchmark for Context Dependence in Object Detection (NeurIPS 2026 · similarity 0.89)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (TPAMI 2016 · similarity 0.88)
- Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection (CVPR 2022 · similarity 0.87)
- Scene Context-Aware Salient Object Detection (ICCV 2021 · similarity 0.87)
- Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection (AAAI 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.
