Proceedings ArticleDOI
Open Set Domain Adaptation
Pau Panareda Busto,Juergen Gall +1 more
- pp 754-763
Reads0
Chats0
TLDR
This work learns a mapping from the source to the target domain by jointly solving an assignment problem that labels those target instances that potentially belong to the categories of interest present in the source dataset.Abstract:
When the training and the test data belong to different domains, the accuracy of an object classifier is significantly reduced. Therefore, several algorithms have been proposed in the last years to diminish the so called domain shift between datasets. However, all available evaluation protocols for domain adaptation describe a closed set recognition task, where both domains, namely source and target, contain exactly the same object classes. In this work, we also explore the field of domain adaptation in open sets, which is a more realistic scenario where only a few categories of interest are shared between source and target data. Therefore, we propose a method that fits in both closed and open set scenarios. The approach learns a mapping from the source to the target domain by jointly solving an assignment problem that labels those target instances that potentially belong to the categories of interest present in the source dataset. A thorough evaluation shows that our approach outperforms the state-of-the-art.read more
Citations
More filters
Journal ArticleDOI
Distance constraint between features for unsupervised domain adaptive person re-identification
TL;DR: A distance constraint between features (DCF) method, which clusters the feature distribution fitted the real target-domain data, which leads the domain adaptive model to enjoy the more reliable clustering results and thus obtain a great identification performance in target domain.
Journal ArticleDOI
Kernelized Unified Domain Adaptation on Geometrical Manifolds
TL;DR: The proposed Unified Domain Adaptation on Geometrical Manifolds (UDAGM) framework optimizes all the aforementioned objectives jointly as well as uses the Regularized Coplanar Discriminant Analysis (RCDA) method for better inter-class separability and intra-class compactness.
Proceedings ArticleDOI
Subsidiary Prototype Alignment for Universal Domain Adaptation
TL;DR: In this article , the tradeoff between negative-transfer-risk and domain-invariance exhibited at different layers of a deep network is explored at a mid-level layer, where word-prototypes are used to represent lower-level visual primitives that are likely to be unaffected by the category-shift in the high-level features.
Journal ArticleDOI
Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition
TL;DR: In this paper, the authors propose a decomposition of the model into the weight parameters and the BN statistics in the training phase to solve the problem of domain adaptation with limited unlabeled samples.
Posted Content
Class-Incremental Domain Adaptation
Jogendra Nath Kundu,Rahul Mysore Venkatesh,Naveen Venkat,Ambareesh Revanur,R. Venkatesh Babu +4 more
TL;DR: In this paper, the authors introduce a practical domain adaptation paradigm called Class-Incremental Domain Adaptation (CIDA), which enables classification of target samples into both shared and one-shot target classes, even under a domain shift.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Proceedings Article
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TL;DR: DeCAF as discussed by the authors is an open-source implementation of these deep convolutional activation features, along with all associated network parameters, to enable vision researchers to conduct experimentation with deep representations across a range of visual concept learning paradigms.
Posted Content
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TL;DR: DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.
Posted Content
Learning Transferable Features with Deep Adaptation Networks
TL;DR: A new Deep Adaptation Network (DAN) architecture is proposed, which generalizes deep convolutional neural network to the domain adaptation scenario and can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding.