Saved in:
Bibliographic Details
Main Authors: Luo, Jiaan, Hong, Feng, Hu, Qiang, Cao, Xiaofeng, Liu, Feng, Yao, Jiangchao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08177
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911200173883392
author Luo, Jiaan
Hong, Feng
Hu, Qiang
Cao, Xiaofeng
Liu, Feng
Yao, Jiangchao
author_facet Luo, Jiaan
Hong, Feng
Hu, Qiang
Cao, Xiaofeng
Liu, Feng
Yao, Jiangchao
contents Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally prevents the model generalization to the tail classes. Despite the promise of previous methods from the perspectives of data augmentation, loss rebalancing and decoupled training etc., consistent improvement in the broad scenarios like multi-label long-tailed recognition is difficult. In this study, we dive into the essential model capacity impact under long-tailed context, and propose a novel framework, Model Rebalancing (MORE), which mitigates imbalance by directly rebalancing the model's parameter space. Specifically, MORE introduces a low-rank parameter component to mediate the parameter space allocation guided by a tailored loss and sinusoidal reweighting schedule, but without increasing the overall model complexity or inference costs. Extensive experiments on diverse long-tailed benchmarks, spanning multi-class and multi-label tasks, demonstrate that MORE significantly improves generalization, particularly for tail classes, and effectively complements existing imbalance mitigation methods. These results highlight MORE's potential as a robust plug-and-play module in long-tailed settings.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08177
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Long-tailed Recognition with Model Rebalancing
Luo, Jiaan
Hong, Feng
Hu, Qiang
Cao, Xiaofeng
Liu, Feng
Yao, Jiangchao
Machine Learning
Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally prevents the model generalization to the tail classes. Despite the promise of previous methods from the perspectives of data augmentation, loss rebalancing and decoupled training etc., consistent improvement in the broad scenarios like multi-label long-tailed recognition is difficult. In this study, we dive into the essential model capacity impact under long-tailed context, and propose a novel framework, Model Rebalancing (MORE), which mitigates imbalance by directly rebalancing the model's parameter space. Specifically, MORE introduces a low-rank parameter component to mediate the parameter space allocation guided by a tailored loss and sinusoidal reweighting schedule, but without increasing the overall model complexity or inference costs. Extensive experiments on diverse long-tailed benchmarks, spanning multi-class and multi-label tasks, demonstrate that MORE significantly improves generalization, particularly for tail classes, and effectively complements existing imbalance mitigation methods. These results highlight MORE's potential as a robust plug-and-play module in long-tailed settings.
title Long-tailed Recognition with Model Rebalancing
topic Machine Learning
url https://arxiv.org/abs/2510.08177