Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
read the original abstract
In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains. We formally demonstrate this hypothesis and, aiming at achieving an optimal alignment in practical cases, we adopt a more principled strategy which, differently from the current Euclidean approaches, deploys alignment along geodesics. Our pipeline can be implemented by adding to the standard classification loss (on the labeled source domain), a source-to-target regularizer that is weighted in an unsupervised and data-driven fashion. We provide extensive experiments to assess the superiority of our framework on standard domain and modality adaptation benchmarks.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse
ZeroSiam is an asymmetric architecture using a learnable predictor and stop-gradient that prevents collapse in test-time entropy minimization while also regularizing biased signals for improved performance.
-
Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift
Presents the first unsupervised source-free framework for ranking semantic and instance segmentation models via prediction consistency under perturbations, with rankings correlating to target-domain performance across...
-
UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition
UniD-Shift decomposes 2D and 3D features into shared semantic and private modality-specific subspaces to enable unified semantic segmentation with improved accuracy and cross-domain generalization on SemanticKITTI and...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.