Reshaping Visual Datasets for Domain Adaptation

By Boqing Gong, Kristen Grauman, Fei Sha. 2013

142 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Multiple-Source Adaptation with Domain Classifiers (2020, background): “…target domain [Mansour et al., 2008, 2009a, Hoffman et al., 2018, Pan and Yang, 2010, Muandet et al., 2013, Xu et al., 2014, Hoffman et al., 2012, Gong et al., 2013a,b, Zhang et al., 2015, Ganin et al., 2016, Tzeng et al., 2015, Motiian et al., 2017b,a, Wang et al., 2019, Konstantinov and…”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, methodology): “This approach has been further used in many applications such as object recognition (Ho↵man et al., 2012; Gong et al., 2013a,b).”
Agnostic Federated Learning (2019, background): “…more closely related to that of federated learning is that of multiple-source adaptation , ﬁrst formalized and analyzed theoretically by Mansour, Mohri, and Rostamizadeh (2009c,a) and later studied for various applications such as object recognition (Hoffman et al., 2012; Gong et al., 2013a,b).”
Algorithms and Theory for Multiple-Source Adaptation (2018, background): “This is known as the multiple-source adaption (MSA) problem ﬁrst formalized and analyzed theoretically by Mansour et al. [2008, 2009] and later studied for various applications such as object recognition [Hoffman et al., 2012, Gong et al., 2013a,b].”
Conditional variance penalties and domain shift robustness (2017, background): “The domain variable D is latent, in contrast to Gong et al. (2016) whose model is shown in panel (a) of Figure 3.”
Domain Generalization for Object Recognition with Multi-task Autoencoders (2015, background): “Dataset bias becomes a signiﬁcant problem when training and test domains differ: applying a classiﬁer trained on one dataset to images sampled from another typically results in poor performance [35, 18].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “ion method can be seen as a sort of two-task learning problem where learning the source speciﬁc task helps learning the target speciﬁc task. Furthermore, in the case of multi-source domain adaptation [143, 67, 227, 265, 220, 116, 200, 102, 107, 52] different source speciﬁc tasks are jointly exploite”
A Deeper Look at Dataset Bias (2015, methodology): “Several domain adaptive methods have been tested on setups extracted from multiple datasets [12,16] and some approaches proposed to identify the latent domains in the data collections before applying domain adaptation solutions [22,14,43].”
Structure-Preserved Multi-source Domain Adaptation (2016, background): “Another example is to mine the latent domains under certain criteria such as domain integrity and separability [7].”
Learning the Roots of Visual Domain Shift (2016, methodology): “Some techniques perform this by simply re-weighting or selecting the samples in the source domain [4,5], or clustering them to search for visually coherent sub-domains [6,7].”
Open Set Domain Adaptation (2017, methodology): “Open set domain adaptation on the unsupervised Office dataset with 10 shared classes (OS) using all samples per class [17].”
Learning Attributes Equals Multi-Source Domain Generalization (2016, background): “Multi-source domain adaptation [49, 29, 24, 71, 15] is related to our approach if we consider a transductive setting (i.”
Discovering Attribute Shades of Meaning with the Crowd (2015, background): “Other approaches find within-category modes in order to perform better domain adaptation for object recognition (Hoffman et al, 2012; Gong et al, 2013; Xiong et al, 2014).”
An introduction to domain adaptation and transfer learning (2018, background): “Manifolds One can make an even stronger assumption than that of the existence of a mapping from source to target domain: that there exists a manifold of transformations between the source and target domain [83,7,104,217].”
Multiple-source adaptation theory and algorithms (2020, background): “Gong et al. [25] proposed to discover multiple latent domains by maximizing two key properties, distinctiveness and learnability, between latent domains.”
Adaptation Across Extreme Variations using Unlabeled Domain Bridges (2019, background): “While works on unsupervised discovery of latent domains exist [20, 17, 18], the choice of bridging domains remains a hard, unsolved problem.”
A Review of Domain Adaptation without Target Labels (2019, background): “A further step can be taken by assuming that there exists a manifold of transformations between the source and target domain [94], [124], [125].”
Gradient Regularized Contrastive Learning for Continual Domain Adaptation (2020, background): “l-rich source domain to an unlabeled target domain. Most of the literature of domain adaptation focus on adapting from source domain to one target domain [1, 2, 3, 4, 5, 6] or multiple target domains [7, 8, 9]. However, many machine learning models deployed in the real-world are exposed to non-stati”
Domain Generalization and Adaptation Using Low Rank Exemplar SVMs (2018, methodology): “com domain into multiple hidden domains [9], [10].”