Feed-Forward Source-Free Domain Adaptation via Class Prototypes

by   Ondrej Bohdal, et al.

Source-free domain adaptation has become popular because of its practical usefulness and no need to access source data. However, the adaptation process still takes a considerable amount of time and is predominantly based on optimization that relies on back-propagation. In this work we present a simple feed-forward approach that challenges the need for back-propagation based adaptation. Our approach is based on computing prototypes of classes under the domain shift using a pre-trained model. It achieves strong improvements in accuracy compared to the pre-trained model and requires only a small fraction of time of existing domain adaptation methods.


page 1

page 2

page 3

page 4


Feed-Forward Source-Free Latent Domain Adaptation via Cross-Attention

We study the highly practical but comparatively under-studied problem of...

Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation

It is a strong prerequisite to access source data freely in many existin...

Adversarial Weighting for Domain Adaptation in Regression

We present a novel instance based approach to handle regression tasks in...

Learning Grouped Convolution for Efficient Domain Adaptation

This paper presents Dokei, an effective supervised domain adaptation met...

ZeroForge: Feedforward Text-to-Shape Without 3D Supervision

Current state-of-the-art methods for text-to-shape generation either req...

Uncertainty-guided Source-free Domain Adaptation

Source-free domain adaptation (SFDA) aims to adapt a classifier to an un...

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Fully test-time adaptation aims to adapt the network model based on sequ...

Please sign up or login with your details

Forgot password? Click here to reset