paper-with-me

Papers

Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification

2023-01-25 · Indel Pal Singh, Enjie Ghorbel, Anis Kacem, Arunkumar Rathinam, Djamila Aouada

In this paper, a discriminator-free adversarial-based Unsupervised Domain Adaptation (UDA) for Multi-Label Image Classification (MLIC) referred to as DDA-MLIC is proposed. Recently, some attempts have been made for introducing adversarial-based UDA methods in the context of MLIC. However, these methods which rely on an additional discriminator subnet present one major shortcoming. The learning of domain-invariant features may harm their task-specific discriminative power, since the classification and discrimination tasks are decoupled. Herein, we propose to overcome this issue by introducing a novel adversarial critic that is directly deduced from the task-specific classifier. Specifically, a two-component Gaussian Mixture Model (GMM) is fitted on the source and target predictions in order to distinguish between two clusters. This allows extracting a Gaussian distribution for each component. The resulting Gaussian distributions are then used for formulating an adversarial loss based on a Frechet distance. The proposed method is evaluated on several multi-label image datasets covering three different types of domain shift. The obtained results demonstrate that DDA-MLIC outperforms existing state-of-the-art methods in terms of precision while requiring a lower number of parameters. The code is publicly available at github.com/cvi2snt/DDA-MLIC.

📄 PDF Abstract BibTeX arXiv:2301.10611

Code (1)

cvi2snt/dda-mlic 공식 구현 pytorch

Tasks

Domain Adaptationimage-classificationImage ClassificationMulti-Label Image ClassificationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

UDAMA: Unsupervised Domain Adaptation through Multi-discriminator Adversarial Training with Noisy Labels Improves Cardio-fitness Prediction

2023-07-31 · Yu Wu, Dimitris Spathis, Hong Jia, Ignacio Perez-Pozuelo 외

Deep learning models have shown great promise in various healthcare monitoring applications. However, most healthcare datasets with high-quality (gold-standard) labels are small-scale, as directly collecting ground truth…

Domain AdaptationTransfer LearningUnsupervised Domain Adaptation

A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation

2018-03-27 · Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong, Richard Socher

Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (…

Domain AdaptationGenerative Adversarial Networkspeech-recognitionSpeech Recognition

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

2020-06-10 · Yong Dai, Jian Liu, Xiancong Ren, Zenglin Xu

Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analysis (SA) aims to leverage useful information in multiple source domains to help do SA in an unlabeled target domain that has no supervised informati…

Domain AdaptationMulti-Source Unsupervised Domain AdaptationSentiment AnalysisTransfer Learning+1

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

2022-04-08 · CVPR 2022 1 · Lin Chen, Huaian Chen, Zhixiang Wei, Xin Jin 외

Adversarial learning has achieved remarkable performances for unsupervised domain adaptation (UDA). Existing adversarial UDA methods typically adopt an additional discriminator to play the min-max game with a feature ext…

Domain AdaptationUnsupervised Domain Adaptation

Dual Adversarial Domain Adaptation

2020-01-01 · Yuntao Du, Zhiwen Tan, Qian Chen, Xiaowen Zhang 외

Unsupervised domain adaptation aims at transferring knowledge from the labeled source domain to the unlabeled target domain. Previous adversarial domain adaptation methods mostly adopt the discriminator with binary or $K…

2kDomain AdaptationMULTI-VIEW LEARNINGUnsupervised Domain Adaptation