# Adversarial Focal Loss: Asking Your Discriminator for Hard Examples

arXiv: https://arxiv.org/abs/2207.07739 · HTML: https://mlsanity.com/paper/2207.07739/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 54 references that are in the map.
- First posted on arXiv 15 Jul 2022.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Numerical Coordinate Regression with Convolutional Neural Networks](https://mlsanity.com/paper/1801.07372/) (2018)
- [Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation](https://mlsanity.com/paper/2012.15175/) (2020)
- [Human pose estimation via Convolutional Part Heatmap Regression](https://mlsanity.com/paper/1609.01743/) (2016)
- [MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network](https://mlsanity.com/paper/1807.04067/) (2018)
- [PoseFix: Model-agnostic General Human Pose Refinement Network](https://mlsanity.com/paper/1812.03595/) (2018)
- [One-Shot Medical Landmark Detection](https://mlsanity.com/paper/2103.04527/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Short Survey on Importance Weighting for Machine Learning](https://mlsanity.com/paper/2403.10175/) (2024)
- [Normative Modeling for AD Diagnosis and Biomarker Identification](https://mlsanity.com/paper/2411.10570/) (2024)

## Abstract (arXiv)

Focal Loss has reached incredible popularity as it uses a simple technique to identify and utilize hard examples to achieve better performance on classification. However, this method does not easily generalize outside of classification tasks, such as in keypoint detection. In this paper, we propose a novel adaptation of Focal Loss for keypoint detection tasks, called Adversarial Focal Loss (AFL). AFL not only is semantically analogous to Focal loss, but also works as a plug-and-chug upgrade for arbitrary loss functions. While Focal Loss requires output from a classifier, AFL leverages a separate adversarial network to produce a difficulty score for each input. This difficulty score can then be used to dynamically prioritize learning on hard examples, even in absence of a classifier. In this work, we show AFL's effectiveness in enhancing existing methods in keypoint detection and verify its capability to re-weigh examples based on difficulty.