Papers › Upcycling Models under Domain and Category Shift

Upcycling Models under Domain and Category Shift

13 Mar 2023CVPR 2023 1arXiv:2303.07110archive 2025-07-28

Sanqing Qu, Tianpei Zou, Florian Roehrbein, Cewu Lu, Guang Chen, DaCheng Tao, Changjun Jiang

Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open problem. Unsupervised Domain Adaptation (UDA), especially recently proposed Source-free Domain Adaptation (SFDA), has become a promising technology to address this issue. Nevertheless, existing SFDA methods require that the source domain and target domain share the same label space, consequently being only applicable to the vanilla closed-set setting. In this paper, we take one step further and explore the Source-free Universal Domain Adaptation (SF-UniDA). The goal is to identify "known" data samples under both domain and category shift, and reject those "unknown" data samples (not present in source classes), with only the knowledge from standard pre-trained source model. To this end, we introduce an innovative global and local clustering learning technique (GLC). Specifically, we design a novel, adaptive one-vs-all global clustering algorithm to achieve the distinction across different target classes and introduce a local k-NN clustering strategy to alleviate negative transfer. We examine the superiority of our GLC on multiple benchmarks with different category shift scenarios, including partial-set, open-set, and open-partial-set DA. Remarkably, in the most challenging open-partial-set DA scenario, GLC outperforms UMAD by 14.8% on the VisDA benchmark. The code is available at https://github.com/ispc-lab/GLC.

PaperPDFConference PDFCodeMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

ispc-lab/glc officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LEAD: Learning Decomposition for Source-free Universal Domain Adaptation (arXiv:2403.03421; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ispc-lab/bmd mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free... (arXiv:2204.02811; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
ispc-lab/glc-plus mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Source-free Universal Domain Adaptation (SF-UniDA) (graph method: Source-free Universal Domain Adaptation (SF-UniDA)). 6 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. SFUniDA entry · level 0 · unverified · 6153fbffb3985887
  2. Classifier model · level 1 · ran · 590aa0969d97b025
  3. Embedding model · level 1 · ran · 85470d3ab6c52602
  4. ResBase model · level 0 · unverified · 380df4780014a94c
  5. VGGBase model · level 0 · unverified · 112349e40ab69ddb
  6. init_weights helper · level 0 · unverified · 7babf7ea472eba97

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.07110") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringDomain AdaptationSource-Free Domain AdaptationUniversal Domain AdaptationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Universal Domain Adaptation DomainNet GLC H-Score 55.1 #3 of 12 Archive leaderboard report
Universal Domain Adaptation DomainNet GLC Source-free yes #3 of 12 Archive leaderboard report
Universal Domain Adaptation Office-31 GLC H-score 87.8 #5 of 12 Archive leaderboard report
Universal Domain Adaptation Office-31 GLC Source-Free yes #5 of 12 Archive leaderboard report
Universal Domain Adaptation Office-Home GLC H-Score 75.6 #6 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home GLC Source-free yes #6 of 14 Archive leaderboard report
Universal Domain Adaptation Office-Home GLC VLM no #6 of 14 Archive leaderboard report
Universal Domain Adaptation VisDA2017 GLC H-score 73.1 #3 of 13 Archive leaderboard report
Universal Domain Adaptation VisDA2017 GLC Source-free yes #3 of 13 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

k-NN

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