# SWA Object Detection

arXiv: https://arxiv.org/abs/2012.12645 · HTML: https://mlsanity.com/paper/2012.12645/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2020.

## Built on by (most cited first, 22 of 22)

- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection](https://mlsanity.com/paper/2211.06368/) (2022)
- [Switch EMA: A Free Lunch for Better Flatness and Sharpness](https://mlsanity.com/paper/2402.09240/) (2024)
- [Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challenge](https://mlsanity.com/paper/2211.11282/) (2022)
- [Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness](https://mlsanity.com/paper/2107.14342/) (2021)
- [VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2305.19688/) (2023)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge](https://mlsanity.com/paper/2112.01072/) (2021)
- [Evaluation of YOLO Models with Sliced Inference for Small Object Detection](https://mlsanity.com/paper/2203.04799/) (2022)
- [Strong Instance Segmentation Pipeline for MMSports Challenge](https://mlsanity.com/paper/2209.13899/) (2022)
- [LUAI Challenge 2021 on Learning to Understand Aerial Images](https://mlsanity.com/paper/2108.13246/) (2021)
- [5th Place Solution for VSPW 2021 Challenge](https://mlsanity.com/paper/2112.06379/) (2021)
- [The Third Place Solution for CVPR2022 AVA Accessibility Vision and Autonomy Challenge](https://mlsanity.com/paper/2206.13718/) (2022)
- [Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone](https://mlsanity.com/paper/2308.05358/) (2023)
- [Augment Before Copy-Paste: Data and Memory Efficiency-Oriented Instance Segmentation Framework for Sport-scenes](https://mlsanity.com/paper/2403.11572/) (2024)
- [MISS: Memory-efficient Instance Segmentation Framework By Visual Inductive Priors Flow Propagation](https://mlsanity.com/paper/2403.11576/) (2024)
- [VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2406.18176/) (2024)
- [Data-Efficient Challenges in Visual Inductive Priors: A Retrospective](https://mlsanity.com/paper/2506.08612/) (2025)
- [CAME-AB: Cross-Modality Attention with Mixture-of-Experts for Antibody Binding Site Prediction](https://mlsanity.com/paper/2509.06465/) (2025)

## Abstract (arXiv)

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 the aforementioned workable policy of performing SWA in object detection, and we consistently achieve ~1.0 AP improvement over various popular detectors on the challenging COCO benchmark, including Mask RCNN, Faster RCNN, RetinaNet, FCOS, YOLOv3 and VFNet. 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: https://github.com/hyz-xmaster/swaobjectdetection .