# RepPoints V2: Verification Meets Regression for Object Detection

arXiv: https://arxiv.org/abs/2007.08508 · HTML: https://mlsanity.com/paper/2007.08508/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 30 of 40)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [Rank & Sort Loss for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.11669/) (2021)
- [LGD: Label-guided Self-distillation for Object Detection](https://mlsanity.com/paper/2109.11496/) (2021)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art](https://mlsanity.com/paper/2309.04902/) (2023)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [Prediction-Guided Distillation for Dense Object Detection](https://mlsanity.com/paper/2203.05469/) (2022)
- [A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation](https://mlsanity.com/paper/2112.09747/) (2021)
- [USB: Universal-Scale Object Detection Benchmark](https://mlsanity.com/paper/2103.14027/) (2021)
- [Continuous Human Action Recognition for Human-Machine Interaction: A Review](https://mlsanity.com/paper/2202.13096/) (2022)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors](https://mlsanity.com/paper/2208.11356/) (2022)
- [CenterNet++ for Object Detection](https://mlsanity.com/paper/2204.08394/) (2022)
- [UniHead: Unifying Multi-Perception for Detection Heads](https://mlsanity.com/paper/2309.13242/) (2023)
- [Location-Sensitive Visual Recognition with Cross-IOU Loss](https://mlsanity.com/paper/2104.04899/) (2021)
- [Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion](https://mlsanity.com/paper/2207.14172/) (2022)
- [PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling](https://mlsanity.com/paper/2104.13876/) (2021)
- [CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point Cloud](https://mlsanity.com/paper/2202.11868/) (2022)
- [RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection](https://mlsanity.com/paper/2110.12130/) (2021)
- [DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection](https://mlsanity.com/paper/2211.13859/) (2022)
- [Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning](https://mlsanity.com/paper/2110.00523/) (2021)
- [Bootstrap Your Object Detector via Mixed Training](https://mlsanity.com/paper/2111.03056/) (2021)
- [R(Det)^2: Randomized Decision Routing for Object Detection](https://mlsanity.com/paper/2204.00794/) (2022)
- [IoU-Enhanced Attention for End-to-End Task Specific Object Detection](https://mlsanity.com/paper/2209.10391/) (2022)

## Abstract (arXiv)

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 texttttest-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 https://github.com/Scalsol/RepPointsV2.