RepPoints V2: Verification Meets Regression for Object Detection

By Yihong Chen, Zheng Zhang, Yue Cao, Liwei Wang, Stephen Lin, Han Hu. 2020

134 citations recorded by the source corpus.

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 provides consistent improvements of about 2.0 mAP over the original RepPoints on the COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on 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. The code is available at this https URL.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021, methodology): “For the ablation study, we consider four typical object detection frameworks: Cascade Mask R-CNN [26, 6], ATSS [71], RepPoints v2 [12], and Sparse RCNN [52] in mmdetection [10].”
End-to-End Semi-Supervised Object Detection with Soft Teacher (2021, methodology): “In theory, our framework is applicable to mainstream object detectors, including single-stage object detectors [15, 17, 21, 30] and two-stage object detectors [22, 9, 5, 35, 34].”
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection (2020, methodology): “The training/testing details follow the descriptions in previous works [18, 4].”
Probabilistic two-stage detection (2021, methodology): “We extend the scale augmentation to set the shorter edge in the range [480,960] for the large model (Zhang et al., 2019; Zhu et al., 2020a; Chen et al., 2020).”
OTA: Optimal Transport Assignment for Object Detection (2021, background): “Another stream of anchor-free detectors [18, 8, 50, 45, 4] view each object as a single or a set of key-points.”
EAPT: Efficient Attention Pyramid Transformer for Image Processing (2021, methodology): “, Cascade Mask R-CNN [28], [29], ATSS [30], RepPoints v2 [31], and Sparse RCNN [32].”
Oriented RepPoints for Aerial Object Detection (2021, background): “this problem, the adaptive points representation are proposed to automatically adjust the displacements locally [18], [19].”