cs.AI updates on arXiv.org 19小时前
Robust Classification under Noisy Labels: A Geometry-Aware Reliability Framework for Foundation Models
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种基于预训练模型(FM)的噪声数据下鲁棒分类框架,通过引入几何信息提升性能,在CIFAR-10和DermaMNIST数据集上展示出优于传统kNN和自适应邻域基线的鲁棒性。

arXiv:2508.00202v1 Announce Type: cross Abstract: Foundation models (FMs) pretrained on large datasets have become fundamental for various downstream machine learning tasks, in particular in scenarios where obtaining perfectly labeled data is prohibitively expensive. In this paper, we assume an FM has to be fine-tuned with noisy data and present a two-stage framework to ensure robust classification in the presence of label noise without model retraining. Recent work has shown that simple k-nearest neighbor (kNN) approaches using an embedding derived from an FM can achieve good performance even in the presence of severe label noise. Our work is motivated by the fact that these methods make use of local geometry. In this paper, following a similar two-stage procedure, reliability estimation followed by reliability-weighted inference, we show that improved performance can be achieved by introducing geometry information. For a given instance, our proposed inference uses a local neighborhood of training data, obtained using the non-negative kernel (NNK) neighborhood construction. We propose several methods for reliability estimation that can rely less on distance and local neighborhood as the label noise increases. Our evaluation on CIFAR-10 and DermaMNIST shows that our methods improve robustness across various noise conditions, surpassing standard K-NN approaches and recent adaptive-neighborhood baselines.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

预训练模型 噪声数据 鲁棒分类 几何信息 kNN
相关文章