Generalized Domain-Adaptive Dictionaries

By Sumit Shekhar, Vishal M. Patel, Hien Van Nguyen, Ramalingam Chellappa. 2013

187 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

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

In Signal Processing

Citations in the corpus

Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations (2021, background): “Only limited attention has been given on sparsity for deep learning architectures [2]; however, some prior techniques exist for domain adaptation on linear models exploiting sparse codes on a shared dictionary between the domains [54, 74].”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, background): “The features are fixed and then a model is trained to align the source and target domains [16, 20, 33, 38, 42, 43, 44].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “A_release_0315. rar 18 Gabriela Csurka Fig. 14 The SDDL proposes to learn a dictionary in a latent common subspace while maintaining the manifold structure of the data. (Image: Courtesy to S. Shekhar [28]) [117] present a semi-supervised subspace co-projection method, which addresses heterogeneous m”
Return of Frustratingly Easy Domain Adaptation (2015, background): “Dictionary learning methods (Shekhar et al. 2013; Huang and Wang 2013) try to learn a dictionary where the difference between the source and target domain is minimized in the new representation.”
Deep Domain Generalization With Structured Low-Rank Constraint (2018, background): “Multi-source adaptation problem [4], [12] is similar to domain generalization, since they both manage to extract the source knowledge and handle the distribution difference across sources.”
Open Set Domain Adaptation (2017, methodology): “Jointly transforming source and target domains into a common low dimensional space was also done together with a conjugate gradient minimisation of a transformation matrix with orthogonality constraints [3] and with dictionary learning to find subspace interpolations [32, 38, 47].”
LSDT: Latent Sparse Domain Transfer Learning for Visual Adaptation (2016, methodology): “[6] proposed a shared domain dictionary learning (SDDL), which assumes that the knowledge of two domains can be integrated into one dictionary D.”
Domain adaptive sparse representation-based classification (2015, methodology): “In this section, we study the convergence properties of the proposed method and briefly discuss the computational timing compared to the dictionary-based domain adaptation algorithms [16], [14].”
Learning Sparse FRAME Models for Natural Image Patterns (2014, result): “resentation for the task of domain transfer on four domain datasets, and compare with published results (Saenko et al. 2010; Gopalan et al. 2011; Gong et al. 2012; Yang et al. 2011; Jhou et al. 2012; Hoffman et al. 2013; Shekhar et al. 2013).”
Joint cross-domain classification and subspace learning for unsupervised adaptation (2014, methodology): “Dictionary learning methods have also been used with the goal of defining new representations that overcome the domain shift [30, 35].”
DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning (2015, methodology): “Sparse representation and dictionary-based methods for domain adaptation [22]–[24] are also gaining a lot of traction .”
Visual Domain Adaptation: A survey of recent advances (2015, methodology): “In other words, assuming L tasks, the joint probability of each task { ( , )} P X Yi i L 1 = is different, but there is only a single distribution P X ^ h of the observation.”
Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings (2020, background): “However, some prior techniques exist for domain adaptation on linear models exploiting sparse codes on a shared dictionary between the domains [47, 71].”
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization (2015, background): “object recognition result in optimization problems that are inefficient to solve [15], [17], [22], [23].”
Structure-Preserved Multi-source Domain Adaptation (2016, background): “the adaptation process to shift the discriminative function from the source domain and applies it for the target domain [35]; Low-rank Transfer Subspace Learning (LTSL) first learns a subspace with the low-rank constraints, then applies PCA or LDA for the adaptation [29]; SGF trains the discriminati”