Robust and Lightweight Image Hash Retrieval via Contrastive Learning and Generative Adversarial Networks

Designing an Image Hash Retrieval Algorithm based on Contrastive Learning and Generative Adversarial Networks

To address the issues of poor robustness and excessive parameters of traditional visual neural networks, this paper proposes a lightweight and robust image hash retrieval algorithm utilizing contrastive learning and generative adversarial networks. By employing self-supervised adversarial training, the algorithm obtains a robust teacher network, and then trains the student network using generative adversarial networks to enhance the network model's robustness. Next, the algorithm imitates immune injection to distill knowledge while effectively compressing the network, ensuring model performance. Finally, an attention mechanism based on convolution modules is utilized to extract the image hash sequence. Experimental results on public datasets indicate that the proposed image hash retrieval algorithm outperforms various benchmark hash retrieval algorithms, with better robustness and fewer model parameters.