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

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

31 Aug 2024arXiv:2409.00397archive 2025-07-28

Munish Monga, Sachin Kumar Giroh, Ankit Jha, Mainak Singha, Biplab Banerjee, Jocelyn Chanussot

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

PaperPDFConference PDFCode

Code

munish30monga/COSMo officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationMulti-target Domain AdaptationOpen-Set Multi-Target Domain AdaptationPrompt Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Set Multi-Target Domain Adaptation MiniDomainNet COSMo H-Score 81.84 #1 of 1 Archive leaderboard report
Open-Set Multi-Target Domain Adaptation Office-31 COSMo H-Score 90.01 #1 of 1 Archive leaderboard report
Open-Set Multi-Target Domain Adaptation Office-Home COSMo H-Score 83.04 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIPFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections