Search Results for author:
Found 4 papers, 2 papers with code
Merge to Mix: Mixing Datasets via Model Merging
Our key insight is that merging models individually fine-tuned on each dataset in a mixture can effectively serve as a surrogate for a model fine-tuned on the entire mixture.
Rethinking VLMs and LLMs for Image Classification
Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness.
Gradual Source Domain Expansion for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) tries to overcome the need for a large labeled dataset by transferring knowledge from a source dataset, with lots of labeled data, to a target dataset, that has no labeled data.
Ranked #7 on
Domain Adaptation
on Office-31
Backprop Induced Feature Weighting for Adversarial Domain Adaptation with Iterative Label Distribution Alignment
Firstly, it lets the domain classifier focus on features that are important for the classification, and, secondly, it couples the classification and adversarial branch more closely.
Ranked #10 on
Domain Adaptation
on Office-31
