Chrome Extension
WeChat Mini Program
Use on ChatGLM

CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection

ICML 2024(2024)

Tianjin University | Shanghai artificial intelligence laboratory | Shanghai Jiao Tong University | IGSNRR | University of Cambridge

Cited 0|Views33
Abstract
Recent vision-language pre-trained models (VL-PTMs) have shown remarkablesuccess in open-vocabulary tasks. However, downstream use cases often involvefurther fine-tuning of VL-PTMs, which may distort their general knowledge andimpair their ability to handle distribution shifts. In real-world scenarios,machine learning systems inevitably encounter both covariate shifts (e.g.,changes in image styles) and semantic shifts (e.g., test-time unseen classes).This highlights the importance of enhancing out-of-distribution (OOD)generalization on covariate shifts and simultaneously detectingsemantic-shifted unseen classes. Thus a critical but underexplored questionarises: How to improve VL-PTMs' generalization ability to closed-set OOD data,while effectively detecting open-set unseen classes during fine-tuning? In thispaper, we propose a novel objective function of OOD detection that also servesto improve OOD generalization. We show that minimizing the gradient magnitudeof energy scores on training data leads to domain-consistent Hessians ofclassification loss, a strong indicator for OOD generalization revealed bytheoretical analysis. Based on this finding, we have developed a unifiedfine-tuning framework that allows for concurrent optimization of both tasks.Extensive experiments have demonstrated the superiority of our method. The codeis available at https://github.com/LinLLLL/CRoFT.
More
Translated text
PDF
Bibtex
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了一个名为CRoFT的统一微调框架,旨在同时优化闭集OOD数据的一般化能力和开放集未见类别的检测能力。

方法】:通过最小化训练数据上能量分数的梯度大小来构建OOD检测的目标函数,并基于此发现发展了一种统一的微调框架。

实验】:实验表明,所提方法在提升VL-PTMs对 covariate shifts的一般化能力和检测open-set unseen classes方面具有优越性,代码可从https://github.com/LinLLLL/CRoFT获取。