Robust and Accurate Object Detection via Adversarial Learning

• Published in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 16617 - 16626
• Main Authors: Chen, Xiangning, Xie, Cihang, Tan, Mingxing, Zhang, Li, Hsieh, Cho-Jui, Gong, Boqing
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2021
• Subjects: Detectors; Distortion; Location awareness; Object detection; Performance gain; Search problems; Training
• ISSN: 2575-7075
• DOI: 10.1109/CVPR46437.2021.01635

Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a pre-trained classifier, we first study how the classifiers' gains from various data augmentations transfer to object detection. The results are discouraging; the gains diminish after fine-tuning in terms of either accuracy or robustness. This work instead augments the fine-tuning stage for object detectors by exploring adversarial examples, which can be viewed as a model-dependent data augmentation. Our method dynamically selects the stronger adversarial images sourced from a detector's classification and localization branches and evolves with the detector to ensure the augmentation policy stays current and relevant. This model-dependent augmentation generalizes to different object detectors better than AutoAugment, a model-agnostic augmentation policy searched based on one particular detector. Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the COCO object detection benchmark. It also improves the detectors' robustness against natural distortions by +3.8 mAP and against domain shift by +1.3 mAP.