# DR Loss: Improving Object Detection by Distributional Ranking

arXiv: https://arxiv.org/abs/1907.10156 · HTML: https://mlsanity.com/paper/1907.10156/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 24 of 24)

- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [One-Shot Object Affordance Detection in the Wild](https://mlsanity.com/paper/2108.03658/) (2021)
- [Rank & Sort Loss for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.11669/) (2021)
- [Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search](https://mlsanity.com/paper/2102.04700/) (2021)
- [AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks](https://mlsanity.com/paper/2103.14026/) (2021)
- [RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses](https://mlsanity.com/paper/2403.01795/) (2024)
- [You Should Look at All Objects](https://mlsanity.com/paper/2207.07889/) (2022)
- [Ranking-Based Siamese Visual Tracking](https://mlsanity.com/paper/2205.11761/) (2022)
- [Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning](https://mlsanity.com/paper/2112.07015/) (2021)
- [Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection](https://mlsanity.com/paper/2207.12042/) (2022)
- [GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking Loss](https://mlsanity.com/paper/2304.00242/) (2023)
- [Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation Strategies](https://mlsanity.com/paper/2403.07113/) (2024)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [A systematic study of the foreground-background imbalance problem in deep learning for object detection](https://mlsanity.com/paper/2306.16539/) (2023)
- [Bucketed Ranking-based Losses for Efficient Training of Object Detectors](https://mlsanity.com/paper/2407.14204/) (2024)
- [QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems](https://mlsanity.com/paper/2508.08957/) (2025)
- [Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections](https://mlsanity.com/paper/2105.03139/) (2021)
- [Searching Parameterized AP Loss for Object Detection](https://mlsanity.com/paper/2112.05138/) (2021)
- [ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection](https://mlsanity.com/paper/2210.04574/) (2022)
- [SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders](https://mlsanity.com/paper/2110.02776/) (2021)
- [Multiresolution Feature Guidance Based Transformer for Anomaly Detection](https://mlsanity.com/paper/2305.14880/) (2023)
- [Hybrid Classification-Regression Adaptive Loss for Dense Object Detection](https://mlsanity.com/paper/2408.17182/) (2024)

## Abstract (arXiv)

Most of object detection algorithms can be categorized into two classes: two-stage detectors and one-stage detectors. Recently, many efforts have been devoted to one-stage detectors for the simple yet effective architecture. Different from two-stage detectors, one-stage detectors aim to identify foreground objects from all candidates in a single stage. This architecture is efficient but can suffer from the imbalance issue with respect to two aspects: the inter-class imbalance between the number of candidates from foreground and background classes and the intra-class imbalance in the hardness of background candidates, where only a few candidates are hard to be identified. In this work, we propose a novel distributional ranking (DR) loss to handle the challenge. For each image, we convert the classification problem to a ranking problem, which considers pairs of candidates within the image, to address the inter-class imbalance problem. Then, we push the distributions of confidence scores for foreground and background towards the decision boundary. After that, we optimize the rank of the expectations of derived distributions in lieu of original pairs. Our method not only mitigates the intra-class imbalance issue in background candidates but also improves the efficiency for the ranking algorithm. By merely replacing the focal loss in RetinaNet with the developed DR loss and applying ResNet-101 as the backbone, mAP of the single-scale test on COCO can be improved from 39.1% to 41.7% without bells and whistles, which demonstrates the effectiveness of the proposed loss function. Code is available at urlhttps://github.com/idstcv/DRloss.