A Literature Survey on Domain Adaptation of Statistical Classifiers

By James J. Jiang. 2007

265 citations recorded by the source corpus.

Subfields: 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 Representation & Self-Supervised Learning

Citations in the corpus

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (2015, methodology): “This is typically handled via domain adaptation (Jiang, 2008).”
Multi-Source Domain Adaptation: A Causal View (2015, background): “For surveys on DA, see, e.g., (Jiang 2008; Pan and Yang 2010; Candela et al. 2009).”
Learning Representations for Counterfactual Inference (2016, background): “In the contextual bandit setting, there is typically an algo-rithm which determines the choice of the action t given the context x .”
Lifelong Learning for Sentiment Classification (2015, background): “…topics and techniques are related to LL, e.g., lifelong learning (Thrun, 1998, Chen and Liu, 2014b, Silver et al., 2013), transfer learning (Jiang, 2008, Pan and Yang, 2010), multi-task learning (Caruana, 1997), never-ending learning (Carlson et al., 2010), self-taught learning (Raina et…”
Efficient Learning of Domain-invariant Image Representations (2013, methodology): “1) Using a subset of the Office and Caltech256 datasets we evaluate multi-class accuracy performance in a standard supervised domain adaptation setting, where all categories have a small number of labeled examples in the target.”
Causal Generative Domain Adaptation Networks (2018, background): “Domain adaption (DA) aims at learning models that can predict well in test (or target) domains by transferring proper information from source to target domains [1, 2].”
Unsupervised domain adaptation in brain lesion segmentation with adversarial networks (2016, methodology): “In this work we investigate unsupervised domain adaptation (UDA) [9].”
A review on the main challenges in automatic plant disease identification based on visible range images (2016, background): “…adaptation support vector machines (Bruzzone&Marconcini, 2010), Bayesian divergence prior (Li& Bilmes, 2007), PAC-Bayesian analysis (Germain, Laviolette, Habrard, & Morvant, 2015), transfer component analysis (Pan, Tsang, Kwok, & Yang, 2011), among others (see Jiang (2008) and Margolis (2011)).”
Domain Adaptation under Target and Conditional Shift (2013, background): “For surveys on domain adaptation for classification, see, e.g., Jiang (2008); Pan & Yang (2010); Candela et al. (2009).”
Domain Adaptation with Coupled Subspaces (2011, background): “Jiang [22] provides a good overview of domain adaptation settings and models”
Classifier adaptation at prediction time (2015, background): “It is studied in the field of domain adaptation, see for example [11, 18] for surveys.”
Domain adaptive sparse representation-based classification (2015, background): “See [17], [18] and [1] for more detailed discussion of recent domain adaptation approaches.”
DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning (2015, background): “A review of domain adaptation methods from machine learning and the natural language processing communities can be found in [32].”
Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision (2016, unknown): “A set of unlabeled real images is used to adapt learning on labeled synthetic images [17].”
Beyond Sharing Weights for Deep Domain Adaptation (2016, background): “Domain Adaptation [3] and Transfer Learning [4] have long been used to overcome this difficulty bymaking it possible to exploit what has been learned in one specific domain, for which enough training data is available, to effectively train classifiers in a related but different domain, where only ve”