# Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning

Source: [Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning](<https://www.sota2.com/research/paper/68fa72961e209131cea57598>)

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

Data updated: 2025-10-28T13:57:05.059Z

Authors: Yuan Zhou, Richang Hong, Yanrong Guo, Lin Liu, Shijie Hao, Hanwang Zhang

Published: 2024-03-17T03:16:59.000Z

## Abstract

In this paper, we propose to tackle Few-Shot Class-Incremental Learning (FSCIL) from a new perspective, i.e., relation disentanglement, which means enhancing FSCIL via disentangling spurious relation between categories. The challenge of disentangling spurious correlations lies in the poor controllability of FSCIL. On one hand, an FSCIL model is required to be trained in an incremental manner and thus it is very hard to directly control relationships between categories of different sessions. On the other hand, training samples per novel category are only in the few-shot setting, which increases the difficulty of alleviating spurious relation issues as well. To overcome this challenge, in this paper, we propose a new simple-yet-effective method, called ConTrollable Relation-disentangLed Few-Shot Class-Incremental Learning (CTRL-FSCIL). Specifically, during the base session, we propose to anchor base category embeddings in feature space and construct disentanglement proxies to bridge gaps between the learning for category representations in different sessions, thereby making category relation controllable. During incremental learning, the parameters of the backbone network are frozen in order to relieve the negative impact of data scarcity. Moreover, a disentanglement loss is designed to effectively guide a relation disentanglement controller to disentangle spurious correlations between the embeddings encoded by the backbone. In this way, the spurious correlation issue in FSCIL can be suppressed. Extensive experiments on CIFAR-100, mini-ImageNet, and CUB-200 datasets demonstrate the effectiveness of our CTRL-FSCIL method.

## 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/2403.11070>)

[PDF](<https://arxiv.org/pdf/2403.11070.pdf>)
