# Towards Accurate One-Stage Object Detection with AP-Loss

arXiv: https://arxiv.org/abs/1904.06373 · HTML: https://mlsanity.com/paper/1904.06373/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2019.

## Built on by (most cited first, 30 of 36)

- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence](https://mlsanity.com/paper/2104.08736/) (2021)
- [Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training](https://mlsanity.com/paper/2107.05031/) (2021)
- [Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search](https://mlsanity.com/paper/2102.04700/) (2021)
- [RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses](https://mlsanity.com/paper/2403.01795/) (2024)
- [Circle Representation for Medical Object Detection](https://mlsanity.com/paper/2110.12093/) (2021)
- [Momentum Accelerates the Convergence of Stochastic AUPRC Maximization](https://mlsanity.com/paper/2107.01173/) (2021)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)
- [Ranking-Based Siamese Visual Tracking](https://mlsanity.com/paper/2205.11761/) (2022)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [MetricOpt: Learning to Optimize Black-Box Evaluation Metrics](https://mlsanity.com/paper/2104.10631/) (2021)
- [Is Underwater Image Enhancement All Object Detectors Need?](https://mlsanity.com/paper/2311.18814/) (2023)
- [Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability](https://mlsanity.com/paper/2209.13262/) (2022)
- [Deep AUC Maximization for Medical Image Classification: Challenges and Opportunities](https://mlsanity.com/paper/2111.02400/) (2021)
- [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)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Revisiting the Loss Weight Adjustment in Object Detection](https://mlsanity.com/paper/2103.09488/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Bucketed Ranking-based Losses for Efficient Training of Object Detectors](https://mlsanity.com/paper/2407.14204/) (2024)
- [Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigm](https://mlsanity.com/paper/2501.02534/) (2025)
- [Imbalanced Classification in Medical Imaging via Regrouping](https://mlsanity.com/paper/2210.12234/) (2022)
- [Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection](https://mlsanity.com/paper/2501.13365/) (2025)
- [Searching Parameterized AP Loss for Object Detection](https://mlsanity.com/paper/2112.05138/) (2021)
- [AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.08894/) (2022)
- [Improving Transformer Based Line Segment Detection with Matched Predicting and Re-ranking](https://mlsanity.com/paper/2502.17766/) (2025)
- [Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detection](https://mlsanity.com/paper/2506.12460/) (2025)
- [Set Prediction for Next-Day Active Fire Forecasting](https://mlsanity.com/paper/2605.10298/) (2026)

## Abstract (arXiv)

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We verify good convergence property of the proposed algorithm theoretically and empirically. Experimental results demonstrate notable performance improvement in state-of-the-art one-stage detectors based on AP-loss over different kinds of classification-losses on various benchmarks, without changing the network architectures. Code is available at https://github.com/cccorn/AP-loss.