mlsanityData to 14 Oct 2026

SWA Object Detection

arXiv 2012.12645 ↗First posted 23 Dec 2020cs.CVcited by 22

Not on the map. Why?

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 .

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

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 5; 2023: 3; 2024: 5; 2025: 2.

22 papers.

Sort:

By area:

  1. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 254
  2. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  3. 2021You Only Look One-level Featurecited by 116
  4. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  5. 2022Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detectioncited by 43
  6. 2024Switch EMA: A Free Lunch for Better Flatness and Sharpnesscited by 9
  7. 2022Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challengecited by 5
  8. 2021Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awarenesscited by 4
  9. 2023VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 4
  10. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
  11. 2021The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challengecited by 2
  12. 2022Evaluation of YOLO Models with Sliced Inference for Small Object Detectioncited by 2
10 more
  1. 2022Strong Instance Segmentation Pipeline for MMSports Challengecited by 1
  2. 2021LUAI Challenge 2021 on Learning to Understand Aerial Imagescited by 0
  3. 20215th Place Solution for VSPW 2021 Challengecited by 0
  4. 2022The Third Place Solution for CVPR2022 AVA Accessibility Vision and Autonomy Challengecited by 0
  5. 2023Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbonecited by 0
  6. 2024Augment Before Copy-Paste: Data and Memory Efficiency-Oriented Instance Segmentation Framework for Sport-scenescited by 0
  7. 2024MISS: Memory-efficient Instance Segmentation Framework By Visual Inductive Priors Flow Propagationcited by 0
  8. 2024VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 0
  9. 2025Data-Efficient Challenges in Visual Inductive Priors: A Retrospectivecited by 0
  10. 2025CAME-AB: Cross-Modality Attention with Mixture-of-Experts for Antibody Binding Site Predictioncited by 0