SSAH: Semi-Supervised Adversarial Deep Hashing with Self-Paced Hard Sample Generation


  • Sheng Jin Harbin Institute of Technology
  • Shangchen Zhou Nanyang Technological University
  • Yao Liu Alibaba Group
  • Chao Chen Alibaba Group
  • Xiaoshuai Sun Xiamen University
  • Hongxun Yao Harbin Institute of Technology
  • Xian-Sheng Hua Alibaba Group



Deep hashing methods have been proved to be effective and efficient for large-scale Web media search. The success of these data-driven methods largely depends on collecting sufficient labeled data, which is usually a crucial limitation in practical cases. The current solutions to this issue utilize Generative Adversarial Network (GAN) to augment data in semi-supervised learning. However, existing GAN-based methods treat image generations and hashing learning as two isolated processes, leading to generation ineffectiveness. Besides, most works fail to exploit the semantic information in unlabeled data. In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework. The SSAH method consists of an adversarial network (A-Net) and a hashing network (H-Net). To improve the quality of generative images, first, the A-Net learns hard samples with multi-scale occlusions and multi-angle rotated deformations which compete against the learning of accurate hashing codes. Second, we design a novel self-paced hard generation policy to gradually increase the hashing difficulty of generated samples. To make use of the semantic information in unlabeled ones, we propose a semi-supervised consistent loss. The experimental results show that our method can significantly improve state-of-the-art models on both the widely-used hashing datasets and fine-grained datasets.




How to Cite

Jin, S., Zhou, S., Liu, Y., Chen, C., Sun, X., Yao, H., & Hua, X.-S. (2020). SSAH: Semi-Supervised Adversarial Deep Hashing with Self-Paced Hard Sample Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11157-11164.



AAAI Technical Track: Vision