Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, the complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.
Code (1)
Tasks
Domain AdaptationUnsupervised Domain AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning from a Complementary-label Source Domain: Theory and Algorithms
In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label d…
Domain AdaptationUnsupervised Domain AdaptationMulti-Speaker End-to-End Speech Synthesis
In this work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of differe…
Speech SynthesisClarinet: A Music Retrieval System
A MIDI based approach for music recognition is proposed and implemented in this paper. Our Clarinet music retrieval system is designed to search piano MIDI files with high recall and speed. We design a novel melody extra…
Melody ExtractionRetrievalVision-based Detection of Acoustic Timed Events: a Case Study on Clarinet Note Onsets
Acoustic events often have a visual counterpart. Knowledge of visual information can aid the understanding of complex auditory scenes, even when only a stereo mixdown is available in the audio domain, \eg identifying whi…
Binary ClassificationOnset DetectionTowards Budget-Friendly Model-Agnostic Explanation Generation for Large Language Models
With Large language models (LLMs) becoming increasingly prevalent in various applications, the need for interpreting their predictions has become a critical challenge. As LLMs vary in architecture and some are closed-sou…
Explanation Generation