DeepAI AI Chat
Log In Sign Up

SWA Object Detection

by   Haoyang Zhang, et al.

Do you want to improve 1.0 AP for your object detector without any inference cost and any change to your detector? Let us tell you such a recipe. It is surprisingly simple: train your detector for an extra 12 epochs using cyclical learning rates and then average these 12 checkpoints as your final detection model. This potent recipe is inspired by Stochastic Weights Averaging (SWA), which is proposed in arXiv:1803.05407 for improving generalization in deep neural networks. We found it also very effective in object detection. In this technique report, we systematically investigate the effects of applying SWA to object detection as well as instance segmentation. Through extensive experiments, we discover a good policy of performing SWA in object detection, and we consistently achieve ∼1.0 AP improvement over various popular detectors on the challenging COCO benchmark. We hope this work will make more researchers in object detection know this technique and help them train better object detectors. Code is available at: .


page 2

page 6

page 7


OneNet: Towards End-to-End One-Stage Object Detection

End-to-end one-stage object detection trailed thus far. This paper disco...

RepPoints V2: Verification Meets Regression for Object Detection

Verification and regression are two general methodologies for prediction...

Scale Match for Tiny Person Detection

Visual object detection has achieved unprecedented ad-vance with the ris...

Enhancing Your Trained DETRs with Box Refinement

We present a conceptually simple, efficient, and general framework for l...

RTMDet: An Empirical Study of Designing Real-Time Object Detectors

In this paper, we aim to design an efficient real-time object detector t...

Train in Germany, Test in The USA: Making 3D Object Detectors Generalize

In the domain of autonomous driving, deep learning has substantially imp...

Rank of Experts: Detection Network Ensemble

The recent advances of convolutional detectors show impressive performan...

Code Repositories


SWA Object Detection

view repo


2021和鲸社区Kesci 水下目标检测算法赛(湛江)(光学图像赛项)

view repo