Continual Learning for Visual Search with Backward Consistent Feature Embedding

TL;DR

This paper proposes a continual learning method for visual search that maintains backward embedding consistency and supports incremental addition of new classes, reducing computational costs and improving long-term search performance.

Contribution

It introduces the first continual learning approach for visual search that ensures backward feature embedding consistency and handles new classes without prior knowledge.

Findings

Effective in maintaining feature consistency across sessions

Supports incremental addition of new classes without retraining from scratch

Reduces computational costs for large gallery sets

Abstract

In visual search, the gallery set could be incrementally growing and added to the database in practice. However, existing methods rely on the model trained on the entire dataset, ignoring the continual updating of the model. Besides, as the model updates, the new model must re-extract features for the entire gallery set to maintain compatible feature space, imposing a high computational cost for a large gallery set. To address the issues of long-term visual search, we introduce a continual learning (CL) approach that can handle the incrementally growing gallery set with backward embedding consistency. We enforce the losses of inter-session data coherence, neighbor-session model coherence, and intra-session discrimination to conduct a continual learner. In addition to the disjoint setup, our CL solution also tackles the situation of increasingly adding new classes for the blurry boundary without assuming all categories known in the beginning and during model update. To our knowledge, this is the first CL method both tackling the issue of backward-consistent feature embedding and allowing novel classes to occur in the new sessions. Extensive experiments on various benchmarks show the efficacy of our approach under a wide range of setups.