CVNov 27, 2023

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model

arXiv:2311.16510v379 citationsh-index: 8
Originality Highly original
AI Analysis

This work addresses domain adaptation for machine learning models when source data is unavailable, representing an incremental advance by integrating multimodal foundation models into the adaptation process.

The paper tackles the problem of source-free domain adaptation by leveraging a frozen multimodal foundation model, proposing a novel method that alternates between customizing the model via prompt learning and distilling knowledge, achieving significant performance improvements over state-of-the-art alternatives.

Source-Free Domain Adaptation (SFDA) aims to adapt a source model for a target domain, with only access to unlabeled target training data and the source model pre-trained on a supervised source domain. Relying on pseudo labeling and/or auxiliary supervision, conventional methods are inevitably error-prone. To mitigate this limitation, in this work we for the first time explore the potentials of off-the-shelf vision-language (ViL) multimodal models (e.g.,CLIP) with rich whilst heterogeneous knowledge. We find that directly applying the ViL model to the target domain in a zero-shot fashion is unsatisfactory, as it is not specialized for this particular task but largely generic. To make it task specific, we propose a novel Distilling multimodal Foundation model(DIFO)approach. Specifically, DIFO alternates between two steps during adaptation: (i) Customizing the ViL model by maximizing the mutual information with the target model in a prompt learning manner, (ii) Distilling the knowledge of this customized ViL model to the target model. For more fine-grained and reliable distillation, we further introduce two effective regularization terms, namely most-likely category encouragement and predictive consistency. Extensive experiments show that DIFO significantly outperforms the state-of-the-art alternatives. Code is here

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