Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Taehoon, Jang, Donghwan, Han, Bohyung
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912730720501760
author Kim, Taehoon
Jang, Donghwan
Han, Bohyung
author_facet Kim, Taehoon
Jang, Donghwan
Han, Bohyung
contents We present a novel training approach, named Merge-and-Bound (M&B) for Class Incremental Learning (CIL), which directly manipulates model weights in the parameter space for optimization. Our algorithm involves two types of weight merging: inter-task weight merging and intra-task weight merging. Inter-task weight merging unifies previous models by averaging the weights of models from all previous stages. On the other hand, intra-task weight merging facilitates the learning of current task by combining the model parameters within current stage. For reliable weight merging, we also propose a bounded update technique that aims to optimize the target model with minimal cumulative updates and preserve knowledge from previous tasks; this strategy reveals that it is possible to effectively obtain new models near old ones, reducing catastrophic forgetting. M&B is seamlessly integrated into existing CIL methods without modifying architecture components or revising learning objectives. We extensively evaluate our algorithm on standard CIL benchmarks and demonstrate superior performance compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
Kim, Taehoon
Jang, Donghwan
Han, Bohyung
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We present a novel training approach, named Merge-and-Bound (M&B) for Class Incremental Learning (CIL), which directly manipulates model weights in the parameter space for optimization. Our algorithm involves two types of weight merging: inter-task weight merging and intra-task weight merging. Inter-task weight merging unifies previous models by averaging the weights of models from all previous stages. On the other hand, intra-task weight merging facilitates the learning of current task by combining the model parameters within current stage. For reliable weight merging, we also propose a bounded update technique that aims to optimize the target model with minimal cumulative updates and preserve knowledge from previous tasks; this strategy reveals that it is possible to effectively obtain new models near old ones, reducing catastrophic forgetting. M&B is seamlessly integrated into existing CIL methods without modifying architecture components or revising learning objectives. We extensively evaluate our algorithm on standard CIL benchmarks and demonstrate superior performance compared to state-of-the-art methods.
title Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.21490