Papers › Bridging Adversarial and Statistical Domain Transfer via Spectral Adaptation Networks

Bridging Adversarial and Statistical Domain Transfer via Spectral Adaptation Networks

25 Feb 2021archive 2025-07-28

Christoph Raab, Philipp Väth, Peter Meier, Frank-Michael Schleif

Statistical and adversarial adaptation are currently two extensive categories of neural network architectures in unsupervised deep domain adaptation. The latter has become the new standard due to its good theoretical foundation and empirical performance. However, there are two shortcomings. First, recent studies show that these approaches focus too much on easily transferable features and thus neglect important discriminative information. Second, adversarial networks are challenging to train. We addressed the first issue by the alignment of transferable spectral properties within an adversarial model to balance the focus between the easily transferable features and the necessary discriminatory features, while at the same time limiting the learning of domain-specific semantics by relevance considerations. Second, we stabilized the discriminator networks training procedure by Spectral Normalization employing the Lipschitz continuous gradients. We provide a theoretical and empirical evaluation of our improved approach and show its effectiveness in a performance study on standard benchmark data sets against various other state of the art methods.

PaperPDFCode

Code

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 Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation ImageCLEF-DA ASAN Accuracy 88.6 #11 of 17 Archive leaderboard report
Domain Adaptation Office-31 ASAN Average Accuracy 90.0 #14 of 40 Archive leaderboard report
Domain Adaptation Office-Home ASAN Accuracy 68.6 #26 of 29 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSpectral Normalization

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