mlsanityData to 7 Oct 2026

Bag of Freebies for Training Object Detection Neural Networks

arXiv 1902.04103 ↗First posted 11 Feb 2019cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Training heuristics greatly improve various image classification model accuracies~citehe2018bag. Object detection models, however, have more complex neural network structures and optimization targets. The training strategies and pipelines dramatically vary among different models. In this works, we explore training tweaks that apply to various models including Faster R-CNN and YOLOv3. These tweaks do not change the model architectures, therefore, the inference costs remain the same. Our empirical results demonstrate that, however, these freebies can improve up to 5% absolute precision compared to state-of-the-art baselines.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 18; 2023: 9; 2024: 1; 2025: 3; 2026: 1.

47 papers.

Sort:

  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  2. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  3. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  4. 2022Syntax-Aware Network for Handwritten Mathematical Expression Recognitioncited by 68
  5. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  6. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  7. 2022The Lie Derivative for Measuring Learned Equivariancecited by 51
  8. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  9. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  10. 2022When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognitioncited by 35
  11. 2021MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detectioncited by 33
  12. 2022Avoiding spurious correlations via logit correctioncited by 32
35 more
  1. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  2. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  3. 2021Network Augmentation for Tiny Deep Learningcited by 23
  4. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  5. 2023DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labelingcited by 14
  6. 2021Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learningcited by 12
  7. 2022Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perceptioncited by 8
  8. 2022A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehensioncited by 5
  9. 2022Evaluating Context for Deep Object Detectorscited by 4
  10. 2023VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 4
  11. 2023Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognitioncited by 4
  12. 2021Data Augmentation for Object Detection via Differentiable Neural Renderingcited by 3
  13. 2021Artificial and beneficial -- Exploiting artificial images for aerial vehicle detectioncited by 3
  14. 2021GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Referencecited by 3
  15. 2023Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyondcited by 3
  16. 2022Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domainscited by 2
  17. 2023MAC: ModAlity Calibration for Object Detectioncited by 2
  18. 2025Scalable and Reliable Multi-agent Reinforcement Learning for Traffic Assignmentcited by 2
  19. 2021Enabling Level-4 Autonomous Driving on a Single 1k Off-the-Shelf Cardcited by 1
  20. 2022D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptationcited by 1
  21. 2022Multi-level and multi-modal feature fusion for accurate 3D object detection in Connected and Automated Vehiclescited by 1
  22. 2024MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolutioncited by 1
  23. 2025Centralized Copy-Paste: Enhanced Data Augmentation Strategy for Wildland Fire Semantic Segmentationcited by 1
  24. 2021Single Stage Class Agnostic Common Object Detection: A Simple Baselinecited by 0
  25. 2021Visual Transformers with Primal Object Queries for Multi-Label Image Classificationcited by 0
  26. 2021An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robotscited by 0
  27. 2022FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devicescited by 0
  28. 2022Adding New Categories in Object Detection Using Few-Shot Copy-Pastecited by 0
  29. 2022Complementary datasets to COCO for object detectioncited by 0
  30. 2022An advanced combination of semi-supervised Normalizing Flow & Yolo (YoloNF) to detect and recognize vehicle license platescited by 0
  31. 2022Formal guarantees for heuristic optimization algorithms used in machine learningcited by 0
  32. 2023Improving the performance of object detection by preserving label distributioncited by 0
  33. 2023Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learningcited by 0
  34. 2025Benchmarking pig detection and tracking under diverse and challenging conditionscited by 0
  35. 2026Domain generalization and synthetic data in object detection: the enabler, the probe, and the gapcited by 0