利用对抗对比学习提升目标检测器对常见损坏的鲁棒性
Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning
AI总结：
本文提出对抗对比学习框架，通过生成实例级对抗样本并优化对比损失，同时增强目标检测器对对抗攻击和常见损坏的鲁棒性，以提升安全关键应用中的可靠性。
摘要：
神经网络已在各个领域引发革命性变革，在自然语言处理和计算机视觉等任务中展现出卓越的准确性。然而，它们对输入样本轻微改变的脆弱性带来了挑战，尤其是在自动驾驶等安全关键应用中。当前方法（例如在训练期间引入失真）在应对不可预见的损坏方面存在不足。本文提出了一种创新的对抗对比学习框架，以同时增强神经网络对对抗攻击和常见损坏的鲁棒性。通过生成实例级对抗样本并优化对比损失，我们的方法促进了能够抵抗对抗扰动并在现实场景中保持鲁棒的表示。随后的对比学习加强了干净样本与其对抗对应物之间的相似性，从而培养出既能抵抗对抗攻击又能抵抗常见失真的表示。通过专注于提升在对抗和现实条件下的性能，我们的方法旨在增强神经网络在安全关键应用（例如在不可预测天气条件下导航的自动驾驶车辆）中的鲁棒性。我们预期该框架将有助于提升神经网络在挑战性环境中的可靠性，促进其在关键任务场景中的广泛采用。
英文摘要：
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges, particularly in safety-critical applications like autonomous driving. Current approaches, such as introducing distortions during training, fall short in addressing unforeseen corruptions. This paper proposes an innovative adversarial contrastive learning framework to enhance neural network robustness simultaneously against adversarial attacks and common corruptions. By generating instance-wise adversarial examples and optimizing contrastive loss, our method fosters representations that resist adversarial perturbations and remain robust in real-world scenarios. Subsequent contrastive learning then strengthens the similarity between clean samples and their adversarial counterparts, fostering representations resistant to both adversarial attacks and common distortions. By focusing on improving performance under adversarial and real-world conditions, our approach aims to bolster the robustness of neural networks in safety-critical applications, such as autonomous vehicles navigating unpredictable weather conditions. We anticipate that this framework will contribute to advancing the reliability of neural networks in challenging environments, facilitating their widespread adoption in mission-critical scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
