FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

no code implementations • 28 Dec 2021 • Sayan Rakshit, Anwesh Mohanty, Ruchika Chavhan, Biplab Banerjee, Gemma Roig, Subhasis Chaudhuri

Inspired by the notion of generative feature replay, 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.

Generative Adversarial Network Unsupervised Domain Adaptation

Behavior of Keyword Spotting Networks Under Noisy Conditions

no code implementations • 15 Sep 2021 • Anwesh Mohanty, Adrian Frischknecht, Christoph Gerum, Oliver Bringmann

Keyword spotting (KWS) is becoming a ubiquitous need with the advancement in artificial intelligence and smart devices.

Keyword Spotting