Towards Adversarially Robust Object Detection

Abstract

Object detection is an important vision task and has emerged as an indispensable component in many vision system, rendering its robustness as an increasingly important performance factor for practical applications. While object detection models have been demonstrated to be vulnerable against adversarial attacks by many recent works, very few efforts have been devoted to improving their robustness. In this work, we take an initial attempt towards this direction. We first revisit and systematically analyze object detectors and many recently developed attacks from the perspective of model robustness. We then present a multi-task learning perspective of object detection and identify an asymmetric role of task losses. We further develop an adversarial training approach which can leverage the multiple sources of attacks for improving the robustness of detection models. Extensive experiments on PASCAL-VOC and MS-COCO verified the effectiveness of the proposed approach.

ICCV 2019

References in corpus (12)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• DSSD : Deconvolutional Single Shot Detector
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• FSSD: Feature Fusion Single Shot Multibox Detector
• Scalable, High-Quality Object Detection
• On Detecting Adversarial Perturbations
• Adversarial Examples that Fool Detectors
• Physical Adversarial Examples for Object Detectors
• Rethinking ImageNet Pre-training
• MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
• Transferable Adversarial Attacks for Image and Video Object Detection