COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation

TL;DR

COSMo introduces a novel prompt learning approach using CLIP for open-set multi-target domain adaptation, effectively handling domain and class shifts with improved performance on multiple datasets.

Contribution

It is the first method to address open-set multi-target domain adaptation by learning domain-agnostic prompts guided by source domain information in the prompt space.

Findings

Achieves an average of 5.1% improvement over existing methods on three datasets.

Effectively handles both open-set and multi-target domain shifts.

Demonstrates the potential of CLIP-based prompt learning for complex domain adaptation tasks.

Abstract

Multi-Target Domain Adaptation (MTDA) entails learning domain-invariant information from a single source domain and applying it to multiple unlabeled target domains. Yet, existing MTDA methods predominantly focus on addressing domain shifts within visual features, often overlooking semantic features and struggling to handle unknown classes, resulting in what is known as Open-Set (OS) MTDA. While large-scale vision-language foundation models like CLIP show promise, their potential for MTDA remains largely unexplored. This paper introduces COSMo, a novel method that learns domain-agnostic prompts through source domain-guided prompt learning to tackle the MTDA problem in the prompt space. By leveraging a domain-specific bias network and separate prompts for known and unknown classes, COSMo effectively adapts across domain and class shifts. To the best of our knowledge, COSMo is the first method to address Open-Set Multi-Target DA (OSMTDA), offering a more realistic representation of real-world scenarios and addressing the challenges of both open-set and multi-target DA. COSMo demonstrates an average improvement of $5.1\%$ across three challenging datasets: Mini-DomainNet, Office-31, and Office-Home, compared to other related DA methods adapted to operate within the OSMTDA setting. Code is available at: https://github.com/munish30monga/COSMo