# Bag of Freebies for Training Object Detection Neural Networks

arXiv: https://arxiv.org/abs/1902.04103 · HTML: https://mlsanity.com/paper/1902.04103/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2019.

## Built on by (most cited first, 30 of 47)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds](https://mlsanity.com/paper/2208.00223/) (2022)
- [Syntax-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2203.01601/) (2022)
- [The Lie Derivative for Measuring Learned Equivariance](https://mlsanity.com/paper/2210.02984/) (2022)
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/2305.04925/) (2023)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Robust and Accurate Object Detection via Adversarial Learning](https://mlsanity.com/paper/2103.13886/) (2021)
- [TransCenter: Transformers with Dense Representations for Multiple-Object Tracking](https://mlsanity.com/paper/2103.15145/) (2021)
- [When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2207.11463/) (2022)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [Avoiding spurious correlations via logit correction](https://mlsanity.com/paper/2212.01433/) (2022)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Network Augmentation for Tiny Deep Learning](https://mlsanity.com/paper/2110.08890/) (2021)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling](https://mlsanity.com/paper/2303.14078/) (2023)
- [Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning](https://mlsanity.com/paper/2104.02230/) (2021)
- [Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception](https://mlsanity.com/paper/2210.14612/) (2022)
- [A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension](https://mlsanity.com/paper/2204.07913/) (2022)
- [Evaluating Context for Deep Object Detectors](https://mlsanity.com/paper/2205.02887/) (2022)
- [VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2305.19688/) (2023)
- [Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2308.10493/) (2023)
- [Data Augmentation for Object Detection via Differentiable Neural Rendering](https://mlsanity.com/paper/2103.02852/) (2021)
- [Artificial and beneficial -- Exploiting artificial images for aerial vehicle detection](https://mlsanity.com/paper/2104.03054/) (2021)
- [GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference](https://mlsanity.com/paper/2106.15064/) (2021)
- [Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond](https://mlsanity.com/paper/2303.10343/) (2023)
- [Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains](https://mlsanity.com/paper/2203.01682/) (2022)
- [MAC: ModAlity Calibration for Object Detection](https://mlsanity.com/paper/2310.09461/) (2023)
- [Scalable and Reliable Multi-agent Reinforcement Learning for Traffic Assignment](https://mlsanity.com/paper/2506.17029/) (2025)

## 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.