ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts

Samar Khanna; Medhanie Irgau; David B. Lobell; Stefano Ermon

2025 ICML ICML 2025

ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Samar Khanna, Medhanie Irgau, David B. Lobell, Stefano Ermon

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Application Areas > Domain Adaptation Deep Learning > Techniques > Pretraining

Keywords

vision transformer unsupervised pretraining linear probing domain shift loras vit blocks

Download PDF