Unsupervised Class-Incremental Learning Through Confusion

04/09/2021
by   Shivam Khare, et al.
3

While many works on Continual Learning have shown promising results for mitigating catastrophic forgetting, they have relied on supervised training. To successfully learn in a label-agnostic incremental setting, a model must distinguish between learned and novel classes to properly include samples for training. We introduce a novelty detection method that leverages network confusion caused by training incoming data as a new class. We found that incorporating a class-imbalance during this detection method substantially enhances performance. The effectiveness of our approach is demonstrated across a set of image classification benchmarks: MNIST, SVHN, CIFAR-10, CIFAR-100, and CRIB.

READ FULL TEXT

page 12

page 13

research
04/14/2021

Continual Learning From Unlabeled Data Via Deep Clustering

Continual learning, a promising future learning strategy, aims to learn ...
research
03/22/2021

Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning

Online class-incremental continual learning (CL) studies the problem of ...
research
07/18/2019

Autoencoder-Based Incremental Class Learning without Retraining on Old Data

Incremental class learning, a scenario in continual learning context whe...
research
05/30/2023

Prediction Error-based Classification for Class-Incremental Learning

Class-incremental learning (CIL) is a particularly challenging variant o...
research
11/10/2022

Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations

Online continual learning (OCL) aims to enable model learning from a non...
research
09/05/2023

Continual Improvement of Threshold-Based Novelty Detection

When evaluated in dynamic, open-world situations, neural networks strugg...
research
01/13/2020

Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation

Like humans, deep networks learn better when samples are organized and i...

Please sign up or login with your details

Forgot password? Click here to reset