Unified Deep Supervised Domain Adaptation and Generalization
Saeid Motiian,Marco Piccirilli,Donald A. Adjeroh,Gianfranco Doretto +3 more
- pp 5716-5726
Reads0
Chats0
TLDR
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models by reverting to point-wise surrogates of distribution distances and similarities by exploiting the Siamese architecture.Abstract:
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models. The main idea is to exploit the Siamese architecture to learn an embedding subspace that is discriminative, and where mapped visual domains are semantically aligned and yet maximally separated. The supervised setting becomes attractive especially when only few target data samples need to be labeled. In this scenario, alignment and separation of semantic probability distributions is difficult because of the lack of data. We found that by reverting to point-wise surrogates of distribution distances and similarities provides an effective solution. In addition, the approach has a high “speed” of adaptation, which requires an extremely low number of labeled target training samples, even one per category can be effective. The approach is extended to domain generalization. For both applications the experiments show very promising results.read more
Citations
More filters
Journal ArticleDOI
Toward Robust Histology-Prior Embedding for Endomicroscopy Image Classification
TL;DR: The proposed stochastic routing normalization and neighborhood embedding framework with application to breast tissue classification by learning discriminative features of probe-based confocal laser endomicroscopy can outperform previous works on domain alignment.
Proceedings ArticleDOI
Domain Generalization via Selective Consistency Regularization for Time Series Classification
TL;DR: In this article , the authors propose a novel representation learning methodology that selectively enforces prediction consistency between source domains estimated to be closely-related, and apply their method to time-series classification tasks.
Journal ArticleDOI
Unsupervised visual domain adaptation via discriminative dictionary evolution
TL;DR: A Discriminative Dictionary Evolution (DDE) approach to seek discriminative features robust to domain shift, which produces domain-invariant representations for cross-domain visual recognition meanwhile promotes the discriminativeness of the dictionary.
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Journal ArticleDOI
The Pascal Visual Object Classes (VOC) Challenge
TL;DR: The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.