ConvNet-based object detection networks have achieved outstanding performance on clean images. However, many works have shown that these detectors perform poorly on corrupted images caused by noises, blurs, poor weather conditions and so on. With the development of security-sensitive applications, the detector’s practicability has raised increasing concerns. Existing approaches improve detector robustness via extra operations (image restoration or training on extra labeled data) or by applying adversarial training at the expense of performance degradation on clean images. In this paper, we present Selective Adversarial Learning with Constraints (SALC) as a universal detector training approach to simultaneously improve the detector’s precision and robustness. We first propose a unified formulation of adversarial samples for multitask adversarial learning, which significantly diversifies the obtained adversarial samples when integrated into the adversarial training of the detector. Next, we examine our findings on model bias against adversarial attacks of different strengths and differences in Batch Normalization (BN) statistics among clean images and different adversarial samples. On this basis, we propose a batch local comparison strategy with two BN branches to balance the detector’s accuracy and robustness. Furthermore, to avoid performance degradation caused by overwhelming subtask losses, we leverage task-aware ratio thresholds to control the influence of learning in each subtask. The proposed approach can be applied to various detectors without any extra labeled data, inference time costs, or model parameters. Extensive experiments show that our SALC achieves state-of-the-art results on both clean benchmarks (Pascal VOC and MS-COCO) and corruption benchmarks (Pascal VOC-C and MS-COCO-C).

中文翻译：

---

通过带约束的选择性对抗性学习实现准确而鲁棒的对象检测


基于 ConvNet 的对象检测网络在干净图像上取得了出色的性能。然而，许多工作表明，这些探测器在由噪声、模糊、恶劣天气条件等引起的损坏图像上表现不佳。随着安全敏感应用的发展，该检测器的实用性引起了越来越多的关注。现有方法通过额外的操作（图像恢复或对额外标记数据进行训练）或通过应用对抗性训练来提高探测器的稳健性，但代价是干净图像的性能下降。在本文中，我们提出了带约束的选择性对抗学习 （SALC） 作为一种通用的检测器训练方法，以同时提高检测器的精度和鲁棒性。我们首先提出了一种用于多任务对抗性学习的对抗性样本的统一公式，当集成到检测器的对抗性训练中时，获得的对抗性样本显着多样化。接下来，我们检查了我们对不同强度的对抗性攻击的模型偏差以及干净图像和不同对抗样本之间批量归一化 （BN） 统计差异的发现。在此基础上，我们提出了一种具有两个 BN 分支的批量局部比较策略，以平衡探测器的准确性和鲁棒性。此外，为了避免因压倒性的 subtask 损失而导致的性能下降，我们利用任务感知比率阈值来控制每个 subtask 中学习的影响。所提出的方法可以应用于各种检测器，而无需任何额外的标记数据、推理时间成本或模型参数。 广泛的实验表明，我们的 SALC 在清洁基准（Pascal VOC 和 MS-COCO）和腐败基准（Pascal VOC-C 和 MS-COCO-C）上都取得了最先进的结果。