LGMar 16, 2024

Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders

arXiv:2403.10800v21 citationsh-index: 12024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
Originality Highly original
AI Analysis

This addresses a critical issue for machine learning practitioners using transfer learning, offering a more robust alternative to fine-tuning for handling distribution shifts.

The paper tackles the problem of fine-tuning pre-trained models degrading out-of-distribution (OOD) performance, introducing Reprogrammer, a model reprogramming approach that outperforms fine-tuning in OOD generalization and detection tasks.

When evaluating the performance of a pre-trained model transferred to a downstream task, it is imperative to assess not only the in-distribution (ID) accuracy of the downstream model but also its capacity to generalize and identify out-of-distribution (OOD) samples. In this paper, we unveil the hidden costs associated with intrusive fine-tuning techniques. Specifically, we demonstrate that commonly used fine-tuning methods not only distort the representations necessary for generalizing to covariate-shifted OOD samples (OOD generalization) but also distort the representations necessary for detecting semantically-shifted OOD samples (OOD detection). To address these challenges, we introduce a new model reprogramming approach for fine-tuning, which we name Reprogrammer. Reprogrammer aims to improve the holistic performance of the downstream model across ID, OOD generalization, and OOD detection tasks. Our empirical evidence reveals that Reprogrammer is less intrusive and yields superior downstream models. Furthermore, we demonstrate that by appending an additional representation residual connection to Reprogrammer, we can further preserve pre-training representations, resulting in an even more safe and robust downstream model capable of excelling in many ID classification, OOD generalization, and OOD detection settings.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes