Timezone: »

 
Poster
RepPoints v2: Verification Meets Regression for Object Detection
Yihong Chen · Zheng Zhang · Yue Cao · Liwei Wang · Stephen Lin · Han Hu

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #490
in Poster Session 2 »

Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement. We introduce verification tasks into the localization prediction of RepPoints, producing RepPoints v2, which proves consistent improvements of about 2.0 mAP over the original RepPoints on COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on the COCO \texttt{test-dev} by a single model. Moreover, we show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation.

Keywords: Learning Theory · Theory

Author Information

Yihong Chen (Peking University)
Zheng Zhang (MSRA)
Yue Cao (Microsoft Research)
Liwei Wang (Peking University)
Stephen Lin (Microsoft Research)
Han Hu (Microsoft Research Asia)

More from the Same Authors