When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks
arXiv:2105.06152
Abstract
Human pose estimation is a fundamental yet challenging task in computer vision, which aims at localizing human anatomical keypoints. However, unlike human vision that is robust to various data corruptions such as blur and pixelation, current pose estimators are easily confused by these corruptions. This work comprehensively studies and addresses this problem by building rigorous robust benchmarks, termed COCO-C, MPII-C, and OCHuman-C, to evaluate the weaknesses of current advanced pose estimators, and a new algorithm termed AdvMix is proposed to improve their robustness in different corruptions. Our work has several unique benefits. (1) AdvMix is model-agnostic and capable in a wide-spectrum of pose estimation models. (2) AdvMix consists of adversarial augmentation and knowledge distillation. Adversarial augmentation contains two neural network modules that are trained jointly and competitively in an adversarial manner, where a generator network mixes different corrupted images to confuse a pose estimator, improving the robustness of the pose estimator by learning from harder samples. To compensate for the noise patterns by adversarial augmentation, knowledge distillation is applied to transfer clean pose structure knowledge to the target pose estimator. (3) Extensive experiments show that AdvMix significantly increases the robustness of pose estimations across a wide range of corruptions, while maintaining accuracy on clean data in various challenging benchmark datasets.
arXiv commentAccepted by CVPR 2021
References in corpus (15)
- mixup: Beyond Empirical Risk Minimization
- Improved Regularization of Convolutional Neural Networks with Cutout
- Random Erasing Data Augmentation
- AutoAugment: Learning Augmentation Policies from Data
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Using Pre-Training Can Improve Model Robustness and Uncertainty
- Generalisation in humans and deep neural networks
- GridMask Data Augmentation
- Examining the Impact of Blur on Recognition by Convolutional Networks
- Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
- Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
- Deep High-Resolution Representation Learning for Human Pose Estimation
- Adversarial Semantic Data Augmentation for Human Pose Estimation