Cgat: Center-guided Adversarial Training For Deep Hashing-based Retrieval

Abstract

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 iterati

Stats

• citations6
• S2 citations—
• github stars10
• HF likes0
• heat score8.42
• arxiv keywang2022cgat

Related papers

• Semantic-aware Adversarial Training For Reliable Deep Hashing Retrieval (2023)13.49
• Targeted Attack For Deep Hashing Based Retrieval (2020)13.65
• Improved Deep Classwise Hashing With Centers Similarity Learning For Image Retrieval (2021)5.84
• Reliable And Efficient Evaluation Of Adversarial Robustness For Deep Hashing-based Retrieval (2023)0.00
• Unsupervised Multi-criteria Adversarial Detection In Deep Image Retrieval (2023)0.00
• Hashgan:attention-aware Deep Adversarial Hashing For Cross Modal Retrieval (2017)15.34
• Deep Hashing With Semantic Hash Centers For Image Retrieval (2025)2.26
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35