DeepAI AI Chat
Log In Sign Up

Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation

by   Idit Diamant, et al.

Source-free domain adaptation (SFDA) aims to transfer knowledge learned from a source domain to an unlabeled target domain, where the source data is unavailable during adaptation. Existing approaches for SFDA focus on self-training usually including well-established entropy minimization techniques. One of the main challenges in SFDA is to reduce accumulation of errors caused by domain misalignment. A recent strategy successfully managed to reduce error accumulation by pseudo-labeling the target samples based on class-wise prototypes (centroids) generated by their clustering in the representation space. However, this strategy also creates cases for which the cross-entropy of a pseudo-label and the minimum entropy have a conflict in their objectives. We call this conflict the centroid-hypothesis conflict. We propose to reconcile this conflict by aligning the entropy minimization objective with that of the pseudo labels' cross entropy. We demonstrate the effectiveness of aligning the two loss objectives on three domain adaptation datasets. In addition, we provide state-of-the-art results using up-to-date architectures also showing the consistency of our method across these architectures.


Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

Conventional unsupervised domain adaptation (UDA) methods need to access...

Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization

Multi-Source Unsupervised Domain Adaptation (multi-source UDA) aims to l...

Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation

Source-Free Domain Adaptation (SFDA) aims to solve the domain adaptation...

Domain Adaptation without Source Data

Domain adaptation assumes that samples from source and target domains ar...

Active Source Free Domain Adaptation

Source free domain adaptation (SFDA) aims to transfer a trained source m...

Appearance Based Deep Domain Adaptation for the Classification of Aerial Images

This paper addresses domain adaptation for the pixel-wise classification...

3D Masked Autoencoding and Pseudo-labeling for Domain Adaptive Segmentation of Heterogeneous Infant Brain MRI

Robust segmentation of infant brain MRI across multiple ages, modalities...