Research map / Detection and segmentation / Open-set and few-shot detection
Multi-Adversarial Faster-RCNN for Unrestricted Object Detection
Zhenwei He, Lei Zhang
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 hierarchical domain feature alignment to proposal alignment (ablation) | MAF · Cityscapes -> Foggy Cityscapes | mAP: 28.5 -> 34.0 | Improved |
| add proposal feature alignment to domain feature alignment (ablation) | MAF · Cityscapes -> Foggy Cityscapes | mAP: 33.6 -> 34.0 | Improved |
| add domain classifiers on blocks 3 and 4 to a single block-5 classifier (ablation) | MAF* · Cityscapes -> Foggy Cityscapes | mAP: 30.9 -> 34.0 | Improved |
| add WGRL in place of standard GRL (ablation) | MAF* · Cityscapes -> Foggy Cityscapes | mAP: 30.3 -> 30.9 | Improved |
| add aggregation of detection results with proposal feature (ablation) | MAF* · Cityscapes -> Foggy Cityscapes | mAP: 30.2 -> 30.9 | Improved |
| add hierarchical domain feature alignment (ablation) | MAF · SIM10k -> Cityscapes | AP: 40.1 -> 41.1 | Improved |
| add proposal feature alignment to domain feature alignment (ablation) | MAF · SIM10k -> Cityscapes | AP: 40.7 -> 41.1 | Improved |
| add hierarchical domain feature alignment (ablation) | MAF · Cityscapes -> KITTI | AP: 69.9 -> 72.1 | Improved |
| add proposal feature alignment to domain feature alignment (ablation) | MAF · KITTI -> Cityscapes | AP: 39.7 -> 41.0 | Improved |
| use MAF instead of DAF | MAF · Cityscapes -> Foggy Cityscapes | mAP: 27.6 -> 34.0 | Improved |
| use MAF instead of DAF | MAF · Cityscapes -> KITTI | AP: 64.1 -> 72.1 | Improved |
| use MAF instead of DAF | MAF · SIM10k -> Cityscapes | AP: 39.0 -> 41.1 | Improved |
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.
- Faster-RCNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 4 of 4 shared results
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
- Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN (ECCV 2020 · similarity 0.92)
- Domain Adaptive Faster R-CNN for Object Detection in the Wild (CVPR 2018 · similarity 0.92)
- Adapting Object Detectors via Selective Cross-Domain Alignment (CVPR 2019 · similarity 0.91)
- Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection (CVPR 2019 · similarity 0.91)
- Multi-Source Domain Adaptation for Object Detection (ICCV 2021 · similarity 0.91)
- Domain-Specific Suppression for Adaptive Object Detection (CVPR 2021 · similarity 0.90)
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.
