FreeAnchor: Learning to Match Anchors for Visual Object Detection
Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner. Our approach, referred to as FreeAnchor, updates hand-crafted anchor assignment to "free" anchor matching by formulating detector training as a maximum likelihood estimation (MLE) procedure. FreeAnchor targets at learning features which best explain a class of objects in terms of both classification and localization. FreeAnchor is implemented by optimizing detection customized likelihood and can be fused with CNN-based detectors in a plug-and-play manner. Experiments on COCO demonstrate that FreeAnchor consistently outperforms their counterparts with significant margins.
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
|---|---|---|---|---|---|---|---|
| R-50 | pytorch | 1x | 4.9 | 18.4 | 38.7 | config | model | log |
| R-101 | pytorch | 1x | 6.8 | 14.9 | 40.3 | config | model | log |
| X-101-32x4d | pytorch | 1x | 8.1 | 11.1 | 41.9 | config | model | log |
Notes:
- We use 8 GPUs with 2 images/GPU.
- For more settings and models, please refer to the official repo.
@inproceedings{zhang2019freeanchor,
title = {{FreeAnchor}: Learning to Match Anchors for Visual Object Detection},
author = {Zhang, Xiaosong and Wan, Fang and Liu, Chang and Ji, Rongrong and Ye, Qixiang},
booktitle = {Neural Information Processing Systems},
year = {2019}
}