Deep continual hashing for real-world multi-label image retrieval

Ge Song, Kai Huang, Hanwen Su, Fengyi Song, Ming Yang

Abstract: Highlights•The code drift is a key problem in continual hash learning for image retrieval.•The two-step hash learning is a useful architecture for continual hash learning.•Keeping label-code pairs can capture the similarities between old and new data.•The combination of different losses can alleviate the code drift of the hashing.•The gradient projection improves the probability of code of old data unchanged.