Open AccessProceedings Article
Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation
Boqing Gong,Kristen Grauman,Fei Sha +2 more
- 16 Jun 2013
- pp 222-230
TL;DR: This paper automatically discovers the existence of landmarks and uses them to bridge the source to the target by constructing provably easier auxiliary domain adaptation tasks, and shows how this composition can be optimized discriminatively without requiring labels from the target domain.
read more
Abstract: Learning domain-invariant features is of vital importance to unsupervised domain adaptation, where classifiers trained on the source domain need to be adapted to a different target domain for which no labeled examples are available. In this paper, we propose a novel approach for learning such features. The central idea is to exploit the existence of landmarks, which are a subset of labeled data instances in the source domain that are distributed most similarly to the target domain. Our approach automatically discovers the landmarks and use them to bridge the source to the target by constructing provably easier auxiliary domain adaptation tasks. The solutions of those auxiliary tasks form the basis to compose invariant features for the original task. We show how this composition can be optimized discriminatively without requiring labels from the target domain. We validate the method on standard benchmark datasets for visual object recognition and sentiment analysis of text. Empirical results show the proposed method outperforms the state-of-the-art significantly.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Face recognition in video surveillance from a single reference sample through domain adaptation
Saman Bashbaghi
- 27 Sep 2017
TL;DR: Adaptive systems are proposed for accurate still-to-video FR that are based on multiple face representations and domain adaptation, especially when individual-specific ensembles are designed using exemplar-SVMs rather than one-class SVMs, and exploit score-level fusion of local SVMs (trained using features extracted from each patch), rather than using either decision-level or feature- level fusion with a global SVM (trained by concatenating features extracting from patches).
1
•Posted Content
Domain adaptation of weighted majority votes via perturbed variation-based self-labeling
TL;DR: In this article, a perturbed variation-based self-labeling approach is proposed to learn a weighted majority vote over a set of real-valued functions in a domain adaptation setting.
1
Unsupervised domain adaptation via transferred local Fisher discriminant analysis
TL;DR: This paper introduces a novel unsupervised domain adaptation method for cross-domain visual classification via transferred local Fisher discriminant analysis (TLFDA), which maximizes the between-class separability and preserves the within-class local structure in form of an objective function metric.
1
Shallow Domain Adaptation
Sanatan Sukhija,Narayanan C. Krishnan +1 more
- 01 Jan 2020
TL;DR: Transfer Learning (TL) as discussed by the authors deals with utilizing knowledge from data-rich auxiliary domains to learn a reliable predictor for the domain of interest, which is referred to as knowledge transfer.
1
Posterior Transfer Learning with Active Sampling
Jie Pan,Yaofeng Tu +1 more
- 20 Dec 2020
TL;DR: A novel strategy to reuse the posterior probabilities from source domains without data sharing and a sampling strategy based on distribution difference is designed to actively select the most valuable instances for label querying is proposed.
1
References
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
LabelMe: A Database and Web-Based Tool for Image Annotation
TL;DR: In this article, a large collection of images with ground truth labels is built to be used for object detection and recognition research, such data is useful for supervised learning and quantitative evaluation.
A theory of learning from different domains
Shai Ben-David,John Blitzer,Koby Crammer,Alex Kulesza,Fernando Pereira,Jennifer Wortman Vaughan +5 more
TL;DR: A classifier-induced divergence measure that can be estimated from finite, unlabeled samples from the domains and shows how to choose the optimal combination of source and target error as a function of the divergence, the sample sizes of both domains, and the complexity of the hypothesis class.
Domain Adaptation via Transfer Component Analysis
TL;DR: This work proposes a novel dimensionality reduction framework for reducing the distance between domains in a latent space for domain adaptation and proposes both unsupervised and semisupervised feature extraction approaches, which can dramatically reduce thedistance between domain distributions by projecting data onto the learned transfer components.