Scale-Aware Trident Networks for Object Detection
About
Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Object Detection | COCO (test-dev) | mAP48.4 | 1239 | |
| Object Detection | MS COCO (test-dev) | mAP@.569.7 | 677 | |
| Object Detection | COCO v2017 (test-dev) | mAP46.8 | 499 | |
| Object Detection | AI-TOD (test) | AP@0.520.9 | 109 | |
| Object Detection | UCAS-AOD (test) | mAP61.5 | 55 | |
| Object Detection | CARPK (test) | AP50 (bbox)89.83 | 35 | |
| Object Detection | LEVIR-Ship (test) | AP5075.1 | 31 | |
| Object Detection | HRPlane v2 (test) | AP@50 (bbox)96.52 | 25 | |
| Object Detection | CORS-ADD (test) | AP (bbox)61.58 | 23 | |
| Object Detection | ADCOS (test) | AP (bbox)70.23 | 23 |