DeepAI AI Chat
Log In Sign Up

Continual Learning for Visual Search with Backward Consistent Feature Embedding

by   Timmy S. T. Wan, et al.
Academia Sinica
National Taiwan University

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.


page 12

page 13


Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

This paper studies continual learning (CL) of a sequence of aspect senti...

PIVOT: Prompting for Video Continual Learning

Modern machine learning pipelines are limited due to data availability, ...

ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation

Session-based recommendation has received growing attention recently due...

Online Continual Learning For Visual Food Classification

Food image classification is challenging for real-world applications sin...

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning

With the success of pretraining techniques in representation learning, a...

Continual Representation Learning for Biometric Identification

With the explosion of digital data in recent years, continuously learnin...

Backward-Compatible Prediction Updates: A Probabilistic Approach

When machine learning systems meet real world applications, accuracy is ...