Papers › Learning multiple visual domains with residual adapters

Learning multiple visual domains with residual adapters

22 May 2017NeurIPS 2017 12arXiv:1705.08045archive 2025-07-28

Sylvestre-Alvise Rebuffi, Hakan Bilen, Andrea Vedaldi

There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs and digits. Inspired by recent work on learning networks that predict the parameters of another, we develop a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains. Our method achieves a high degree of parameter sharing while maintaining or even improving the accuracy of domain-specific representations. We also introduce the Visual Decathlon Challenge, a benchmark that evaluates the ability of representations to capture simultaneously ten very different visual domains and measures their ability to recognize well uniformly.

PaperPDFConference PDFCode

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

srebuffi/residual_adapters officialpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient parametrization of multi-domain deep neural networks (arXiv:1803.10082; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
YuWang24/MultiTune 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.

Tasks

Continual Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continual Learning visual domain decathlon (10 tasks) Res. adapt. (large) decathlon discipline (Score) 3131 #6 of 14 Archive leaderboard report
Continual Learning visual domain decathlon (10 tasks) Res. adapt. finetune all decathlon discipline (Score) 2643 #9 of 14 Archive leaderboard report
Continual Learning visual domain decathlon (10 tasks) Res. adapt. decay decathlon discipline (Score) 2621 #10 of 14 Archive leaderboard report
Continual Learning visual domain decathlon (10 tasks) Res. adapt. dom-pred decathlon discipline (Score) 2503 #12 of 14 Archive leaderboard report
Continual Learning visual domain decathlon (10 tasks) Res. adapt. decathlon discipline (Score) 2118 #13 of 14 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.

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