paper-with-me

Papers

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

2018-11-30 · CVPR 2019 6 · Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, Patrick Pérez

Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a major challenge. In numerous real world applications, there is indeed a large gap between data distributions in train and test domains, which results in severe performance loss at run-time. In this work, we address the task of unsupervised domain adaptation in semantic segmentation with losses based on the entropy of the pixel-wise predictions. To this end, we propose two novel, complementary methods using (i) entropy loss and (ii) adversarial loss respectively. We demonstrate state-of-the-art performance in semantic segmentation on two challenging "synthetic-2-real" set-ups and show that the approach can also be used for detection.

📄 PDF Abstract BibTeX arXiv:1811.12833

Code (4)

valeoai/ADVENT 공식 구현 pytorch
attm/tensorflow_advent tf
thuml/Transfer-Learning-Library pytorch
yuan-zm/dgt-st pytorch

Tasks

Domain AdaptationImage-to-Image TranslationSegmentationSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Entropy Minimization vs. Diversity Maximization for Domain Adaptation

2020-02-05 · Xiaofu Wu, Suofei hang, Quan Zhou, Zhen Yang 외

Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to a…

DiversityDomain AdaptationUnsupervised Domain Adaptation

Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptation

2020-08-19 · Artjoms Gorpincenko, Geoffrey French, Michal Mackiewicz

Virtual Adversarial Training has recently seen a lot of success in semi-supervised learning, as well as unsupervised Domain Adaptation. However, so far it has been used on input samples in the pixel space, whereas we pro…

Domain AdaptationUnsupervised Domain Adaptation

Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation

2022-12-07 · Idit Diamant, Roy H. Jennings, Oranit Dror, Hai Victor Habi 외

Source-free domain adaptation (SFDA) aims to transfer knowledge learned from a source domain to an unlabeled target domain, where the source data is unavailable during adaptation. Existing approaches for SFDA focus on se…

Domain AdaptationPseudo LabelSource-Free Domain Adaptation

Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification

2023-08-04 · Menglong Lu, Zhen Huang, Zhiliang Tian, Yunxiang Zhao 외

Text classification is a fundamental task for natural language processing, and adapting text classification models across domains has broad applications. Self-training generates pseudo-examples from the model's predictio…

Domain AdaptationMeta-Learningtext-classificationText Classification

Co-Regularized Adversarial Learning for Multi-Domain Text Classification

2022-01-30 · Yuan Wu, Diana Inkpen, Ahmed El-Roby

Multi-domain text classification (MDTC) aims to leverage all available resources from multiple domains to learn a predictive model that can generalize well on these domains. Recently, many MDTC methods adopt adversarial …

Classificationtext-classificationText Classification