Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation

TL;DR

This paper introduces Prompt Ensemble Self-training (PEST), a novel framework leveraging vision-language models for open-vocabulary domain adaptation, enabling effective transfer to unlabelled target domains with different vocabularies.

Contribution

The paper proposes PEST, a new self-training method that uses multiple prompts and temporal ensemble techniques to improve open-vocabulary domain adaptation with vision-language models.

Findings

PEST outperforms state-of-the-art methods on 10 image recognition tasks.

Effective mitigation of domain discrepancies through prompt ensemble techniques.

Enhanced learning of image-text correspondences in unlabelled target domains.

Abstract

Traditional domain adaptation assumes the same vocabulary across source and target domains, which often struggles with limited transfer flexibility and efficiency while handling target domains with different vocabularies. Inspired by recent vision-language models (VLMs) that enable open-vocabulary visual recognition by reasoning on both images and texts, we study open-vocabulary domain adaptation (OVDA), a new unsupervised domain adaptation framework that positions a pre-trained VLM as the source model and transfers it towards arbitrary unlabelled target domains. To this end, we design a Prompt Ensemble Self-training (PEST) technique that exploits the synergy between vision and language to mitigate the domain discrepancies in image and text distributions simultaneously. Specifically, PEST makes use of the complementary property of multiple prompts within and across vision and language modalities, which enables joint exploitation of vision and language information and effective learning of image-text correspondences in the unlabelled target domains. Additionally, PEST captures temporal information via temporal prompt ensemble which helps memorize previously learnt target information. Extensive experiments show that PEST outperforms the state-of-the-art consistently across 10 image recognition tasks.