# Libra R-CNN: Towards Balanced Learning for Object Detection

arXiv: https://arxiv.org/abs/1904.02701 · HTML: https://mlsanity.com/paper/1904.02701/

## Key facts

- Cited by 255 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 255)

- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [AdaMixer: A Fast-Converging Query-Based Object Detector](https://mlsanity.com/paper/2203.16507/) (2022)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Towards Accurate Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2303.14341/) (2023)
- [Diversifying Sample Generation for Accurate Data-Free Quantization](https://mlsanity.com/paper/2103.01049/) (2021)
- [QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking](https://mlsanity.com/paper/2210.06984/) (2022)
- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [Accelerating DETR Convergence via Semantic-Aligned Matching](https://mlsanity.com/paper/2203.06883/) (2022)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding](https://mlsanity.com/paper/2104.04386/) (2021)
- [Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery](https://mlsanity.com/paper/2112.02991/) (2021)
- [Label Matching Semi-Supervised Object Detection](https://mlsanity.com/paper/2206.06608/) (2022)
- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [Dual-stream Network for Visual Recognition](https://mlsanity.com/paper/2105.14734/) (2021)
- [YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection](https://mlsanity.com/paper/2308.05480/) (2023)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)

## Abstract (arXiv)

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level. To mitigate the adverse effects caused thereby, we propose Libra R-CNN, a simple but effective framework towards balanced learning for object detection. It integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level. Benefitted from the overall balanced design, Libra R-CNN significantly improves the detection performance. Without bells and whistles, it achieves 2.5 points and 2.0 points higher Average Precision (AP) than FPN Faster R-CNN and RetinaNet respectively on MSCOCO.