论文标题
CGAT：基于深哈希检索的中心引导对抗训练
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval
论文作者
论文摘要
由于其效率和有效性，深层散列已被广泛用于大量图像检索。但是，深层散列模型容易受到对抗性示例的影响，这使得开发以图像检索的对抗性防御方法至关重要。现有的解决方案获得了有限的防御性能，因为使用弱的对抗样本进行训练，并且缺乏歧视性优化目标来学习强大的功能。在本文中，我们提出了一种基于最小的中心指导的对抗训练，即CGAT，以通过最坏的对抗性例子来提高深层散列网络的稳健性。具体而言，我们首先将中心代码作为输入图像含量的语义歧视代表制定，从而保留了语义相似性，其语义相似性与正面样本和否定示例相似。我们证明，数学公式可以立即计算中心代码。在深度哈希网络的每个优化迭代中获得了中心代码后，它们被采用以指导对抗性训练过程。一方面，CGAT通过最大程度地提高对抗性示例和中心代码之间的哈希码之间的锤击距离来生成最坏的对抗示例作为增强数据。另一方面，CGAT学会通过最大程度地减少与中心代码的锤击距离来减轻对抗样品的影响。基准数据集上的广泛实验证明了我们的对抗训练算法在防御对抗性攻击方面的有效性。与当前的最新防御方法相比，我们在Flickr-25K，NUS范围内和MS-Coco上平均将防御性能显着提高了18.61 \％，12.35 \％和11.56 \％。该代码可在https://github.com/xunguangwang/cgat上找到。
Deep hashing has been extensively utilized in massive image retrieval because of its efficiency and effectiveness. However, deep hashing models are vulnerable to adversarial examples, making it essential to develop adversarial defense methods for image retrieval. Existing solutions achieved limited defense performance because of using weak adversarial samples for training and lacking discriminative optimization objectives to learn robust features. In this paper, we present a min-max based Center-guided Adversarial Training, namely CgAT, to improve the robustness of deep hashing networks through worst adversarial examples. Specifically, we first formulate the center code as a semantically-discriminative representative of the input image content, which preserves the semantic similarity with positive samples and dissimilarity with negative examples. We prove that a mathematical formula can calculate the center code immediately. After obtaining the center codes in each optimization iteration of the deep hashing network, they are adopted to guide the adversarial training process. On the one hand, CgAT generates the worst adversarial examples as augmented data by maximizing the Hamming distance between the hash codes of the adversarial examples and the center codes. On the other hand, CgAT learns to mitigate the effects of adversarial samples by minimizing the Hamming distance to the center codes. Extensive experiments on the benchmark datasets demonstrate the effectiveness of our adversarial training algorithm in defending against adversarial attacks for deep hashing-based retrieval. Compared with the current state-of-the-art defense method, we significantly improve the defense performance by an average of 18.61\%, 12.35\%, and 11.56\% on FLICKR-25K, NUS-WIDE, and MS-COCO, respectively. The code is available at https://github.com/xunguangwang/CgAT.
