FROD: Robust Object Detection for Free
This addresses a critical gap in robust object detection for computer vision systems, though it is incremental as it builds on existing adversarial training methods.
The paper tackles the problem of object detectors being vulnerable to adversarial perturbations by proposing modifications to adversarially trained classification backbones, achieving robustness without computational overhead and demonstrating effectiveness on MS-COCO and Pascal VOC datasets.
Object detection is a vital task in computer vision and has become an integral component of numerous critical systems. However, state-of-the-art object detectors, similar to their classification counterparts, are susceptible to small adversarial perturbations that can significantly alter their normal behavior. Unlike classification, the robustness of object detectors has not been thoroughly explored. In this work, we take the initial step towards bridging the gap between the robustness of classification and object detection by leveraging adversarially trained classification models. Merely utilizing adversarially trained models as backbones for object detection does not result in robustness. We propose effective modifications to the classification-based backbone to instill robustness in object detection without incurring any computational overhead. To further enhance the robustness achieved by the proposed modified backbone, we introduce two lightweight components: imitation loss and delayed adversarial training. Extensive experiments on the MS-COCO and Pascal VOC datasets are conducted to demonstrate the effectiveness of our proposed approach.