Prototype Reminding for Continual Learning

05/23/2019
by   Mengmi Zhang, et al.
5

Continual learning is a critical ability of continually acquiring and transferring knowledge without catastrophically forgetting previously learned knowledge. However, enabling continual learning for AI remains a long-standing challenge. In this work, we propose a novel method, Prototype Reminding, that efficiently embeds and recalls previously learnt knowledge to tackle catastrophic forgetting issue. In particular, we consider continual learning in classification tasks. For each classification task, our method learns a metric space containing a set of prototypes where embedding of the samples from the same class cluster around prototypes and class-representative prototypes are separated apart. To alleviate catastrophic forgetting, our method preserves the embedding function from the samples to the previous metric space, through our proposed prototype reminding from previous tasks. Specifically, the reminding process is implemented by replaying a small number of samples from previous tasks and correspondingly matching their embedding to their nearest class-representative prototypes. Compared with recent continual learning methods, our contributions are fourfold: first, our method achieves the best memory retention capability while adapting quickly to new tasks. Second, our method uses metric learning for classification, and does not require adding in new neurons given new object classes. Third, our method is more memory efficient since only class-representative prototypes need to be recalled. Fourth, our method suggests a promising solution for few-shot continual learning. Without tampering with the performance on initial tasks, our method learns novel concepts given a few training examples of each class in new tasks.

READ FULL TEXT
research
12/03/2018

Few-Shot Self Reminder to Overcome Catastrophic Forgetting

Deep neural networks are known to suffer the catastrophic forgetting pro...
research
10/09/2022

Few-Shot Continual Active Learning by a Robot

In this paper, we consider a challenging but realistic continual learnin...
research
08/03/2022

Centroids Matching: an efficient Continual Learning approach operating in the embedding space

Catastrophic forgetting (CF) occurs when a neural network loses the info...
research
07/15/2022

Continual Learning For On-Device Environmental Sound Classification

Continuously learning new classes without catastrophic forgetting is a c...
research
07/14/2022

In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory

Continually learning new classes from a few training examples without fo...
research
04/22/2020

Continual Learning of Object Instances

We propose continual instance learning - a method that applies the conce...
research
06/10/2019

Generative Continual Concept Learning

After learning a concept, humans are also able to continually generalize...

Please sign up or login with your details

Forgot password? Click here to reset