FRIDA — Generative feature replay for incremental domain adaptation

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are incrementally observed with the constraint that data corresponding to the current domain is only available at a time. The goal is to preserve the accuracies for all the past domains while generalizing well for the current domain. We propose a novel framework called Feature Replay based Incremental Domain Adaptation (FRIDA) which leverages a new incremental generative adversarial network (GAN) called domain-generic auxiliary classification GAN (DGAC-GAN) for producing domain-specific feature representations seamlessly.

Please find the paper

If you find this work useful, please cite our paper

@article{RAKSHIT2022103367,
title = {FRIDA — Generative feature replay for incremental domain adaptation},
journal = {Computer Vision and Image Understanding},
year = {2022},
author = {Sayan Rakshit and Anwesh Mohanty and Ruchika Chavhan and Biplab Banerjee and Gemma Roig and Subhasis Chaudhuri},
}