mlsanityData to 7 Oct 2026

Bootstrap Your Object Detector via Mixed Training

arXiv 2111.03056 ↗First posted 4 Nov 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training. In addition, it addresses localization noise and missing labels in human annotations by incorporating pseudo boxes that can compensate for these errors. Both of these MixTraining capabilities are made possible through bootstrapping on the detector, which can be used to predict the difficulty of training on a strong augmentation, as well as to generate reliable pseudo boxes thanks to the robustness of neural networks to labeling error. MixTraining is found to bring consistent improvements across various detectors on the COCO dataset. In particular, the performance of Faster R-CNN citeren2015faster with a ResNet-50 citehe2016deep backbone is improved from 41.7 mAP to 44.0 mAP, and the accuracy of Cascade-RCNN citecai2018cascade with a Swin-Small citeliu2021swin backbone is raised from 50.9 mAP to 52.8 mAP. The code and models will be made publicly available at urlhttps://github.com/MendelXu/MixTraining.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 38 of its 42 references that are in the map. First posted on arXiv 4 Nov 2021.

Builds on

38 of 42 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  12. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
26 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  3. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  6. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  7. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  8. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  9. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  10. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  11. 2017Relation Networks for Object Detectioncited by 305
  12. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  13. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  14. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  15. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 188
  16. 2017Deep Learning is Robust to Massive Label Noisecited by 164
  17. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  18. 2020Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Trainingcited by 103
  19. 2020AutoAssign: Differentiable Label Assignment for Dense Object Detectioncited by 100
  20. 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
  21. 2019Region Proposal by Guided Anchoringcited by 87
  22. 2020RepPoints V2: Verification Meets Regression for Object Detectioncited by 40
  23. 2020Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detectioncited by 29
  24. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  25. 2017Few-Example Object Detection with Model Communicationcited by 12
  26. 2021Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detectioncited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3.

3 papers.

  1. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  2. 2022Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detectioncited by 6
  3. 2022Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)cited by 1