发表机构
Westlake University; Shandong University; Hokkaido University; RIKEN（西湖大学; 山东大学; 北海道大学; 日本理化学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长尾学习中尾部类别因背景偏置而性能下降的问题，提出OFBD框架，通过前景引导CutMix和背景引导特征修正从分布与优化两方面去偏，显著提升尾部类别准确率且可即插即用。
AI 中文摘要
在长尾数据分布上平衡性能权衡仍然是视觉识别中一个长期存在的挑战。现有方法主要通过重平衡、表示学习或数据增强来改善尾部类别，但尾部类别性能下降的根本原因仍未得到充分探索。在本文中，我们发现标准的长尾训练会导致背景偏置的表示和优化：尾部类别遭受更大的背景分布偏移，并日益受背景梯度的驱动。这表明尾部性能下降不仅是由样本不足引起的，还源于对无关背景特征的学习。为解决这一问题，我们提出了目标聚焦背景去偏（OFBD）框架，从分布和优化两个角度缓解背景偏置。具体而言，前景引导的CutMix在保留与目标相关的前景的同时，使互补背景多样化；背景引导的特征修正无需可学习参数或额外训练即可抑制背景偏置特征。大量实验表明，我们的方法提高了整体准确率，在尾部类别上取得了显著提升，并且无需外部数据或预训练识别模型即可作为主流长尾方法的即插即用模块。代码可在以下网址获取：此https URL
英文摘要
Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, representation learning, or data augmentation, but the underlying cause of tail class degradation is still insufficiently explored. In this paper, we find that standard long-tailed training induces background-biased representation and optimization: tail classes suffer larger background distribution shifts and become increasingly driven by background gradients. This reveals that tail degradation is not merely caused by insufficient samples, but also by the learning of irrelevant background features. To tackle this issue, we propose Object-Focused Background Debiasing (OFBD), a framework that mitigates background bias from both distribution and optimization perspectives. Specifically, Foreground-guided CutMix preserves target-related foregrounds while diversifying complementary backgrounds, and Background-guided Feature Rectification suppresses background-biased features without learnable parameters or additional training. Extensive experiments show that our method improves overall accuracy, achieves significant tail-class gains, and can serve as a plug-in for mainstream long-tailed methods without external data or pretrained recognition models. The code is available at: https://ofbd-neurips2026-longtail-learning.github.io/
