Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labelling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labelling

Résumé

Semi-supervised domain adaptation methods leverage information from a source labelled domain with the goal of generalizing over a scarcely labelled target domain. While this setting already poses challenges due to potential distribution shifts between domains, an even more complex scenario arises when source and target data differs in modality representation (e.g. they are acquired by sensors with different characteristics). For instance, in remote sensing, images may be collected via various acquisition modes (e.g. optical or radar), different spectral characteristics (e.g. RGB or multi-spectral) and spatial resolutions. Such a setting is denoted as Semi-Supervised Heterogeneous Domain Adaptation (SSHDA) and it exhibits an even more severe distribution shift due to modality heterogeneity across domains. To cope with the challenging SSHDA setting, here we introduce SHeDD (Semi-supervised Heterogeneous Domain Adaptation via Disentanglement) an end-to-end neural framework tailored to learning a target domain classifier by leveraging both labelled and unlabelled data from heterogeneous data sources. SHeDD is designed to effectively disentangle domain-invariant representations, relevant for the downstream task, from domain-specific information, that can hinder the cross-modality transfer. Additionally, SHeDD adopts an augmentation-based consistency regularization mechanism that takes advantages of reliable pseudo-labels on the unlabelled target samples to further boost its generalization ability on the target domain. Empirical evaluations on two remote sensing benchmarks, encompassing heterogeneous data in terms of acquisition modes and spectral/spatial resolutions, demonstrate the quality of SHeDD compared to both baseline and state-of-the-art competing approaches. Our code is publicly available here: https://github.com/tanodino/SSHDA/
Fichier principal
Vignette du fichier
main.pdf (841.19 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04617917 , version 1 (19-06-2024)

Identifiants

  • HAL Id : hal-04617917 , version 1

Citer

Cassio F. Dantas, Raffaele Gaetano, Dino Ienco. Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labelling. ECML PKDD: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Sep 2024, Vilnius, Lithuania. ⟨hal-04617917⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More