A Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes

no code implementations • 7 Sep 2023 • Sandipan Choudhuri, Suli Adeniye, Arunabha Sen

This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy.

Ensemble Learning Partial Domain Adaptation +1

Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation

no code implementations • 3 Dec 2022 • Sandipan Choudhuri, Suli Adeniye, Arunabha Sen, Hemanth Venkateswara

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets.

domain classification Partial Domain Adaptation +2