A Multi-Head Model for Continual Learning via Out-of-Distribution Replay

08/20/2022
by   Gyuhak Kim, et al.
1

This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of all tasks in a single head network. To prevent CF, a popular approach is to memorize a small number of samples from previous tasks and replay them during training of the new task. However, this approach still suffers from serious CF as the parameters learned for previous tasks are updated or adjusted with only the limited number of saved samples in the memory. This paper proposes an entirely different approach that builds a separate classifier (head) for each task (called a multi-head model) using a transformer network, called MORE. Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification head) without updating the network learned for previous tasks/classes. The model for the new task in MORE is trained to learn the classes of the task and also to detect samples that are not from the same data distribution (i.e., out-of-distribution (OOD)) of the task. This enables the classifier for the task to which the test instance belongs to produce a high score for the correct class and the classifiers of other tasks to produce low scores because the test instance is not from the data distributions of these classifiers. Experimental results show that MORE outperforms state-of-the-art baselines and is also naturally capable of performing OOD detection in the continual learning setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/23/2022

Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning

Online continual learning, especially when task identities and task boun...
research
06/22/2023

Learnability and Algorithm for Continual Learning

This paper studies the challenging continual learning (CL) setting of Cl...
research
03/23/2023

First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning

In Class-Incremental Learning (CIL) an image classification system is ex...
research
06/23/2023

Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework

The Long-Tailed Recognition (LTR) problem emerges in the context of lear...
research
06/22/2020

Automatic Recall Machines: Internal Replay, Continual Learning and the Brain

Replay in neural networks involves training on sequential data with memo...
research
12/01/2022

GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes

Current deep learning classifiers, carry out supervised learning and sto...
research
05/09/2023

DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors

Modern advances in machine learning (ML) and wearable medical sensors (W...

Please sign up or login with your details

Forgot password? Click here to reset