Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

By Ting Yao, Yingwei Pan, Chong-Wah Ngo, Houqiang Li, Tao Mei. 2015

228 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Few-Shot Adversarial Domain Adaptation (2017, background): “Domain Adaptation can be supervised [58, 27], unsupervised [15, 34], or semi-supervised [16, 21, 63], depending on what data is available in a labeled format and how much can be collected.”
Unified Deep Supervised Domain Adaptation and Generalization (2017, background): “Domain adaptation can be either supervised [60, 33], unsupervised [38, 38, 61], or semi-supervised [26, 29, 67].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “recting Output Codes (ECOC) to address the multi-class aspect and to enhance the discriminative informativeness of the projected subspace. The Semi-supervised Domain Adaptation with Subspace Learning [118] jointly explores invariant lowdimensional structures across domains to correct data distributi”
An introduction to domain adaptation and transfer learning (2018, methodology): “It has been extended a number of times: there is a landmark-based kernelized alignment [3], a subspace distribution alignment technique [183] and a semi-supervised variant [209].”
Reducing Domain Gap by Reducing Style Bias (2021, background): “It is commonly addressed by simultaneously minimizing the distance between the domains as well as imposing a regularization constraint on the target data to prevent overﬁt-ting [7, 50].”
Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition (2016, methodology): “We compared LMIBDA against LMK, the heterogeneous domain adaptation method (HFA) [12], the geodesic flow kernel method (GFK) [21], and against a recent semi-supervised domain adaptation method (SDASL) [50], which uses some labeled target data for training.”
Semi-Supervised Domain Adaptation via Minimax Entropy (2019, methodology): “We show our method’s superiority to existing methods on benchmark datasets for domain adaptation. 2. Related Work Domain Adaptation. Semi-supervised domain adaptation (SSDA) is a very important task [8, 40, 1], however it has not been fully explored, especially with regard to deep learning based met”
Exploring Object Relation in Mean Teacher for Cross-Domain Detection (2019, methodology): “Thus, inspired from graph structure exploitation [31, 32, 51, 52] in computer vision tasks, we devise a novel graph-structured regularization, i.”
Transfer Neural Trees for Heterogeneous Domain Adaptation (2016, methodology): “[24] presented the approach of semi-supervised domain adaptation with subspace learning (SDASL), which minimizes the prediction risk while preserving the locality structure and manifold information for HDA.”
Fully Convolutional Adaptation Networks for Semantic Segmentation (2018, background): “However, many previous experiences have also shown that reapplying a model learnt on synthetic data may hurt the performance in real data due to a phenomenon known as “domain shift” [35].”
Open Set Domain Adaptation (2017, background): “Since CNN features show some robustness to domain changes [11], several domain adaptation approaches based on CNNs have been proposed [39, 31, 45, 48].”
Fast Generalized Distillation for Semi-Supervised Domain Adaptation (2017, methodology): “Previous work in SDA required access to the source data to measure the data distribution mismatch between the source and target domains (Duan et al. 2009; Donahue et al. 2013; Daumé III, Kumar, and Saha 2010; Yao et al. 2015).”
Reducing Domain Gap via Style-Agnostic Networks (2019, methodology): “It is commonly addressed by simultaneously minimizing the distance between the domains as well as imposing a regularization constraint on the target data to prevent overfitting [7,50].”
Transferrable Prototypical Networks for Unsupervised Domain Adaptation (2019, background): “A common practice in unsupervised domain adaptation is to align data distributions between source and target domains or build invariance across domains by minimizing domain shift through measures such as correlation distances [27, 34] or maximum mean discrepancy [31].”