Research map / Detection and segmentation / CNN features
CoupleNet: Coupling Global Structure With Local Parts for Object Detection
Yousong Zhu, Chaoyang Zhao, Jinqiao Wang, Xu Zhao, Yi Wu, Hanqing Lu
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 a local part-sensitive branch coupled with a global branch (CoupleNet instead of R-FCN) | R-FCN · VOC07 test (07+12) | mAP (%): 79.5 -> 81.7 | Improved |
| add global RoI-pooling branch to the local branch (couple with Global FCN) (ablation) | Global FCN · VOC07 test (reimplementation) | mAP (%): 78.5 -> 81.7 | Improved |
| add context region (2x proposal size) to the global branch (ablation) | CoupleNet · VOC07 test (07+12) | mAP (%): 81.7 -> 82.1 | Improved |
| add multi-scale training (ablation) | CoupleNet with context · VOC07 test (07+12) | mAP (%): 82.1 -> 82.7 | Improved |
| add a learned 1x1 conv scale normalization before summing the branches (ablation) | CoupleNet with element-wise sum · VOC07 test (single-scale, no context) | mAP (%): 81.1 -> 81.7 | Improved |
| use L2 normalization on branch outputs instead of none (ablation) | CoupleNet with element-wise sum · VOC07 test (single-scale, no context) | mAP (%): 81.1 -> 80.3 | Hurt |
| use element-wise product instead of sum when coupling (with L2 normalization) (ablation) | CoupleNet · VOC07 test (single-scale, no context) | mAP (%): 80.3 -> 63.5 | Hurt |
| use element-wise sum instead of element-wise max when coupling (1x1 conv) (ablation) | CoupleNet · VOC07 test (single-scale, no context) | mAP (%): 81.3 -> 81.7 | Improved |
| couple global and local branches in one network instead of ensembling two models (ablation) | R-FCN reimplementation · VOC07 test (reimplementation) | mAP (%): 79.4 -> 81.7 | Improved |
| ensemble Faster R-CNN and R-FCN (ablation) | R-FCN reimplementation · VOC07 test (reimplementation) | mAP (%): 78.6 -> 79.6 | Improved |
| add one extra prediction head (same parameter count) to R-FCN (ablation) | R-FCN · VOC07 test (reimplementation) | mAP (%): 78.6 -> 78.8 | No clear effect |
| add the local branch and context at a small inference cost | R-FCN · VOC07 test inference time | ms/img: 83 -> 102 | Hurt |
Later papers that compared with this method
3 later accepted papers report CoupleNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Enriched Feature Guided Refinement Network for Object Detection (ICCV 2019 · better on 0 of 1 shared result)
- Single-Shot Refinement Neural Network for Object Detection (CVPR 2018 · better on 2 of 2 shared results)
- Dynamic Filtering with Large Sampling Field for ConvNets (ECCV 2018 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- R-FCN — R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016) · better on 3 of 4 shared results
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 3 of 3 shared results
- HyperNet — HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection (CVPR 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
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.92)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016 · similarity 0.92)
- R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection (AAAI 2018 · similarity 0.91)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (TPAMI 2016 · similarity 0.90)
- Object Detection Based on Region Decomposition and Assembly (AAAI 2019 · similarity 0.88)
- Object Detection Networks on Convolutional Feature Maps (TPAMI 2016 · similarity 0.88)
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.
