# Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation Strategies

arXiv: https://arxiv.org/abs/2403.07113 · HTML: https://mlsanity.com/paper/2403.07113/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.05830/) (2015)
- [Gradient Harmonized Single-stage Detector](https://mlsanity.com/paper/1811.05181/) (2018)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [FreeAnchor: Learning to Match Anchors for Visual Object Detection](https://mlsanity.com/paper/1909.02466/) (2019)
- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [Prime Sample Attention in Object Detection](https://mlsanity.com/paper/1904.04821/) (2019)
- [Factors in Finetuning Deep Model for object detection](https://mlsanity.com/paper/1601.05150/) (2016)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [Towards Accurate One-Stage Object Detection with AP-Loss](https://mlsanity.com/paper/1904.06373/) (2019)

## Built on by (most cited first, 4 of 4)

- [Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection](https://mlsanity.com/paper/2508.18729/) (2025)
- [An AI-Powered Autonomous Underwater System for Sea Exploration and Scientific Research](https://mlsanity.com/paper/2512.07652/) (2025)
- [BEM: Training-Free Background Embedding Memory for False-Positive Suppression in Real-Time Fixed-Background Camera](https://mlsanity.com/paper/2604.11714/) (2026)
- [Edge AI for Automotive Vulnerable Road User Safety: Deployable Detection via Knowledge Distillation](https://mlsanity.com/paper/2604.26857/) (2026)

## Abstract (arXiv)

Object detection, a pivotal task in computer vision, is frequently hindered by dataset imbalances, particularly the under-explored issue of foreground-foreground class imbalance. This lack of attention to foreground-foreground class imbalance becomes even more pronounced in the context of single-stage detectors. This study introduces a benchmarking framework utilizing the YOLOv5 single-stage detector to address the problem of foreground-foreground class imbalance. We crafted a novel 10-class long-tailed dataset from the COCO dataset, termed COCO-ZIPF, tailored to reflect common real-world detection scenarios with a limited number of object classes. Against this backdrop, we scrutinized three established techniques: sampling, loss weighing, and data augmentation. Our comparative analysis reveals that sampling and loss reweighing methods, while shown to be beneficial in two-stage detector settings, do not translate as effectively in improving YOLOv5's performance on the COCO-ZIPF dataset. On the other hand, data augmentation methods, specifically mosaic and mixup, significantly enhance the model's mean Average Precision (mAP), by introducing more variability and complexity into the training data. (Code available: https://github.com/craston/object_detection_cib)