Timezone: »

Feed-Forward Source-Free Latent Domain Adaptation via Cross-Attention
Ondrej Bohdal · Da Li · Xu Hu · Timothy Hospedales
Event URL: https://openreview.net/forum?id=EiQB09V5IX »

We study the highly practical but comparatively under-studied problem of latent-domain adaptation, where a source model should be adapted to a target dataset that contains a mixture of unlabelled domain-relevant and domain-irrelevant examples. Motivated by the requirements for data privacy and the need for embedded and resource-constrained devices of all kinds to adapt to local data distributions, we further focus on the setting of feed-forward source-free domain adaptation, where adaptation should not require access to the source dataset, and also be back propagation-free. Our solution is to meta-learn a network capable of embedding the mixed-relevance target dataset and dynamically adapting inference for target examples using cross-attention. The resulting framework leads to consistent strong improvements.

Author Information

Ondrej Bohdal (University of Edinburgh)
Da Li (Samsung)
Xu Hu (Ecole des Ponts ParisTech)
Timothy Hospedales (Samsung AI Centre / University of Edinburgh)

More from the Same Authors