Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Reframing Long-Tailed Learning via Loss Landscape Geometry

About

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/.

Shenghan Chen, Yiming Liu, Yanzhen Wang, Yujia Wang, Xiankai Lu• 2026

Related benchmarks

TaskDatasetResultRank
Image ClassificationImageNet LT
Top-1 Accuracy58.9
264
Image ClassificationiNaturalist 2018 (test)
Top-1 Accuracy74.4
207
Image ClassificationImageNet-LT (test)--
159
Image ClassificationCIFAR-10-LT (IF 50)
Top-1 Accuracy88.2
48
Image ClassificationCIFAR-100 LT (IF=50)
Top-1 Acc57.6
42
Image ClassificationCIFAR100 LT (r=100)
Top-1 Accuracy53.2
22
Image ClassificationCIFAR-10-LT
Top-1 Accuracy86.3
17
Image ClassificationCIFAR100 LT (r=10)
Top-1 Accuracy68.7
16
Image ClassificationCIFAR10-LT r=10
Top-1 Accuracy92.5
14
Showing 9 of 9 rows

Other info

Follow for update