Domain Adaptation From Multiple Sources: A Domain-Dependent Regularization Approach
By Lixin Duan, Dong Xu, Ivor Wai-Hung Tsang. 2012
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Learning with Augmented Features for Heterogeneous Domain Adaptation (2012, methodology): “used for different research fields such as natural language processing and computer vision (Blitzer et al., 2006; 2007; Daum´e III, 2007; Duan et al., 2010; 2012b;a; Wu & Dietterich, 2004).”
- Generalized Transfer Subspace Learning Through Low-Rank Constraint (2014, methodology): “More and more research effort is being devoted to visual domain adaptation (Yang et al. 2007; Jiang et al. 2008; Wang et al. 2008; Duan et al. 2009, 2012a,b,c; Si et al. 2010; Saenko et al. 2010; Gopalan et al. 2011; Kulis et al. 2011; Aytar and Zisserman 2011; Qi et al. 2011; Lim et al. 2011; Gong…”
- Recognizing RGB Images by Learning from RGB-D Data (2014, methodology): “For example, Duan et al. [7] proposed a learning method called DAM by using the virtual labels generated from pre-learnt classifiers.”
- Exploiting Low-Rank Structure from Latent Domains for Domain Generalization (2014, methodology): “, p(tu|W)] with each entry p(tj |W) defined in (14) being the “virtual label” for the target sample tj as in DAM [13].”
- Deep Transfer Network: Unsupervised Domain Adaptation (2015, methodology): “It directly designs an adaptive classifier by incorporating distribution adaptation with model regularization [7, 23, 20].”
- Collaborative and Adversarial Network for Unsupervised Domain Adaptation (2018, background): “Existing domain adaptation methods can be roughly categorized as feature (transform) based approaches [1, 11, 17], which aims to seek new domain-invariant features or learn new feature transforms for domain adaptation, and classifier based approaches [8, 9, 4, 7, 5, 29, 10], which directly learn the”
- Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation (2016, background): “…(Pan et al. 2011; Gong et al. 2012; Long et al. 2014c), (2) classifier adaptation (Bruzzone and Marconcini 2010; Bahadori, Liu, and Zhang 2011; Duan, Xu, and Tsang 2012; Ni, Qiu, and Chellappa 2013), (3) deep feature adaptation (Glorot, Bordes, and Bengio 2011; Mesnil et al. 2012; Chen et al.…”
- Multi-view Domain Generalization for Visual Recognition (2015, methodology): “The existing domain adaptation methods can be roughly categorized into feature-based methods [20, 19, 1, 17], classifier-based methods [6, 14, 13, 15, 27], and instance-reweighting methods [24].”
- Shared Predictive Cross-Modal Deep Quantization (2018, unknown): “Actually, cross-modal retrieval has been widely studied in recent years [15]–[22].”
- Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization (2015, methodology): “DAM is expected to provide a better performance, since it is specifically designed for domain adaptation.”
- Adaptive SVM+: Learning with Privileged Information for Domain Adaptation (2017, methodology): “It has been applied with great success in applications ranging from cross-domain setups [9, 11, 38], to facial action unit detection in transductive learning setup [7], to deep neural networks [12, 39].”
- Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition (2016, background): “Moreover, it is also different than multi-domain adaptation methods [11] because we consider a source domain with an auxiliary view.”