SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation

Understand

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.