# Towards Robust Feature Learning with t-vFM Similarity for Continual Learning

Source: [Towards Robust Feature Learning with t-vFM Similarity for Continual Learning](<https://www.sota2.com/research/paper/68fa6fa01e209131cea46b90>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:24:25.039Z

Authors: Bilan Gao, YoungBin Kim

Published: 2023-06-04T11:52:59.000Z

## Abstract

Continual learning has been developed using standard supervised contrastive loss from the perspective of feature learning. Due to the data imbalance during the training, there are still challenges in learning better representations. In this work, we suggest using a different similarity metric instead of cosine similarity in supervised contrastive loss in order to learn more robust representations. We validate the our method on one of the image classification datasets Seq-CIFAR-10 and the results outperform recent continual learning baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.02335>)

[PDF](<https://arxiv.org/pdf/2306.02335.pdf>)