S2IL: Structurally Stable Incremental Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Balasubramanian, S, P, Yedu Krishna, Sriram, Talasu Sai, Subramaniam, M Sai, Sai, Manepalli Pranav Phanindra, Gera, Darshan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909538515419136
author Balasubramanian, S
P, Yedu Krishna
Sriram, Talasu Sai
Subramaniam, M Sai
Sai, Manepalli Pranav Phanindra
Gera, Darshan
author_facet Balasubramanian, S
P, Yedu Krishna
Sriram, Talasu Sai
Subramaniam, M Sai
Sai, Manepalli Pranav Phanindra
Gera, Darshan
contents Feature Distillation (FD) strategies are proven to be effective in mitigating Catastrophic Forgetting (CF) seen in Class Incremental Learning (CIL). However, current FD approaches enforce strict alignment of feature magnitudes and directions across incremental steps, limiting the model's ability to adapt to new knowledge. In this paper we propose Structurally Stable Incremental Learning(S22IL), a FD method for CIL that mitigates CF by focusing on preserving the overall spatial patterns of features which promote flexible (plasticity) yet stable representations that preserve old knowledge (stability). We also demonstrate that our proposed method S2IL achieves strong incremental accuracy and outperforms other FD methods on SOTA benchmark datasets CIFAR-100, ImageNet-100 and ImageNet-1K. Notably, S2IL outperforms other methods by a significant margin in scenarios that have a large number of incremental tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12193
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle S2IL: Structurally Stable Incremental Learning
Balasubramanian, S
P, Yedu Krishna
Sriram, Talasu Sai
Subramaniam, M Sai
Sai, Manepalli Pranav Phanindra
Gera, Darshan
Computer Vision and Pattern Recognition
Machine Learning
Feature Distillation (FD) strategies are proven to be effective in mitigating Catastrophic Forgetting (CF) seen in Class Incremental Learning (CIL). However, current FD approaches enforce strict alignment of feature magnitudes and directions across incremental steps, limiting the model's ability to adapt to new knowledge. In this paper we propose Structurally Stable Incremental Learning(S22IL), a FD method for CIL that mitigates CF by focusing on preserving the overall spatial patterns of features which promote flexible (plasticity) yet stable representations that preserve old knowledge (stability). We also demonstrate that our proposed method S2IL achieves strong incremental accuracy and outperforms other FD methods on SOTA benchmark datasets CIFAR-100, ImageNet-100 and ImageNet-1K. Notably, S2IL outperforms other methods by a significant margin in scenarios that have a large number of incremental tasks.
title S2IL: Structurally Stable Incremental Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.12193