Saved in:
Bibliographic Details
Main Authors: Chen, Shenghan, Liu, Yiming, Wang, Yanzhen, Wang, Yujia, Lu, Xiankai
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.21217
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911535367979008
author Chen, Shenghan
Liu, Yiming
Wang, Yanzhen
Wang, Yujia
Lu, Xiankai
author_facet Chen, Shenghan
Liu, Yiming
Wang, Yanzhen
Wang, Yujia
Lu, Xiankai
contents Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely overfit on head classes while quickly forgetting tail classes) and pose a solution from a loss landscape perspective. We observe that different classes possess divergent convergence points in the loss landscape. Besides, this divergence is aggravated when the model settles into sharp and non-robust minima, rather than a shared and flat solution that is beneficial for all classes. In light of this, we propose a continual learning inspired framework to prevent "tail performance degradation". To avoid inefficient per-class parameter preservation, a Grouped Knowledge Preservation module is proposed to memorize group-specific convergence parameters, promoting convergence towards a shared solution. Concurrently, our framework integrates a Grouped Sharpness Aware module to seek flatter minima by explicitly addressing the geometry of the loss landscape. Notably, our framework requires neither external training samples nor pre-trained models, facilitating the broad applicability. Extensive experiments on four benchmarks demonstrate significant performance gains over state-of-the-art methods. The code is available at:https://gkp-gsa.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21217
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reframing Long-Tailed Learning via Loss Landscape Geometry
Chen, Shenghan
Liu, Yiming
Wang, Yanzhen
Wang, Yujia
Lu, Xiankai
Computer Vision and Pattern Recognition
Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely overfit on head classes while quickly forgetting tail classes) and pose a solution from a loss landscape perspective. We observe that different classes possess divergent convergence points in the loss landscape. Besides, this divergence is aggravated when the model settles into sharp and non-robust minima, rather than a shared and flat solution that is beneficial for all classes. In light of this, we propose a continual learning inspired framework to prevent "tail performance degradation". To avoid inefficient per-class parameter preservation, a Grouped Knowledge Preservation module is proposed to memorize group-specific convergence parameters, promoting convergence towards a shared solution. Concurrently, our framework integrates a Grouped Sharpness Aware module to seek flatter minima by explicitly addressing the geometry of the loss landscape. Notably, our framework requires neither external training samples nor pre-trained models, facilitating the broad applicability. Extensive experiments on four benchmarks demonstrate significant performance gains over state-of-the-art methods. The code is available at:https://gkp-gsa.github.io/.
title Reframing Long-Tailed Learning via Loss Landscape Geometry
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.21217