scholarly journals Adversarial Hard Attention Adaptation

Information ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 224
Author(s):  
Hui Tao ◽  
Jun He ◽  
Quanjie Cao ◽  
Lei Zhang
Keyword(s):  
Visual Attention ◽  
Domain Knowledge ◽  
Domain Adaptation ◽  
Experimental Results ◽  
Target Domain ◽  
Source Domain ◽  
Visual Attention Model ◽  
Attention Model ◽  
Cross Domain ◽  
Adversarial Training

Domain adaptation is critical to transfer the invaluable source domain knowledge to the target domain. In this paper, for a particular visual attention model, saying hard attention, we consider to adapt the learned hard attention to the unlabeled target domain. To tackle this kind of hard attention adaptation, a novel adversarial reward strategy is proposed to train the policy of the target domain agent. In this adversarial training framework, the target domain agent competes with the discriminator which takes the attention features generated from the both domain agents as input and tries its best to distinguish them, and thus the target domain policy is learned to align the local attention feature to its source domain counterpart. We evaluated our model on the benchmarks of the cross-domain tasks, such as the centered digits datasets and the enlarged non-centered digits datasets. The experimental results show that our model outperforms the ADDA and other existing methods.

scholarly journals AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows

2020 ◽  
Vol 34 (04) ◽  
pp. 4028-4035 ◽  
Author(s):  
Aditya Grover ◽  
Christopher Chute ◽  
Rui Shu ◽  
Zhangjie Cao ◽  
Stefano Ermon
Keyword(s):  
Domain Adaptation ◽  
Likelihood Estimation ◽  
Learning Objectives ◽  
Target Domain ◽  
Modeling Framework ◽  
Source Domain ◽  
Cross Domain ◽  
Generative Modeling ◽  
Adversarial Training ◽  
Multiple Domains

Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain adaptation. We propose AlignFlow, a generative modeling framework that models each domain via a normalizing flow. The use of normalizing flows allows for a) flexibility in specifying learning objectives via adversarial training, maximum likelihood estimation, or a hybrid of the two methods; and b) learning and exact inference of a shared representation in the latent space of the generative model. We derive a uniform set of conditions under which AlignFlow is marginally-consistent for the different learning objectives. Furthermore, we show that AlignFlow guarantees exact cycle consistency in mapping datapoints from a source domain to target and back to the source domain. Empirically, AlignFlow outperforms relevant baselines on image-to-image translation and unsupervised domain adaptation and can be used to simultaneously interpolate across the various domains using the learned representation.

scholarly journals Optimal Transport with Dimensionality Reduction for Domain Adaptation

Symmetry ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 1994
Author(s):  
Ping Li ◽  
Zhiwei Ni ◽  
Xuhui Zhu ◽  
Juan Song ◽  
Wenying Wu
Keyword(s):  
Dimensionality Reduction ◽  
Optimal Transport ◽  
Domain Adaptation ◽  
Wasserstein Distance ◽  
Local Information ◽  
Target Domain ◽  
Source Domain ◽  
Second Stage ◽  
Cross Domain ◽  
Feature Based

Domain adaptation manages to learn a robust classifier for target domain, using the source domain, but they often follow different distributions. To bridge distribution shift between the two domains, most of previous works aim to align their feature distributions through feature transformation, of which optimal transport for domain adaptation has attract researchers’ interest, as it can exploit the local information of the two domains in the process of mapping the source instances to the target ones by minimizing Wasserstein distance between their feature distributions. However, it may weaken the feature discriminability of source domain, thus degrade domain adaptation performance. To address this problem, this paper proposes a two-stage feature-based adaptation approach, referred to as optimal transport with dimensionality reduction (OTDR). In the first stage, we apply the dimensionality reduction with intradomain variant maximization but source intraclass compactness minimization, to separate data samples as much as possible and enhance the feature discriminability of the source domain. In the second stage, we leverage optimal transport-based technique to preserve the local information of the two domains. Notably, the desirable properties in the first stage can mitigate the degradation of feature discriminability of the source domain in the second stage. Extensive experiments on several cross-domain image datasets validate that OTDR is superior to its competitors in classification accuracy.

scholarly journals Distributional Correspondence Indexing for Cross-Lingual and Cross-Domain Sentiment Classification (Extended Abstract)

2018 ◽  
Author(s):  
Alejandro Moreo Fernández ◽  
Andrea Esuli ◽  
Fabrizio Sebastiani
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Sentiment Classification ◽  
Training Data ◽  
Target Domain ◽  
Source Domain ◽  
Machine Learning Methods ◽  
Cross Domain ◽  
Current State ◽  
Cross Lingual

Domain Adaptation (DA) techniques aim at enabling machine learning methods learn effective classifiers for a “target” domain when the only available training data belongs to a different “source” domain. In this extended abstract, we briefly describe our new DA method called Distributional Correspondence Indexing (DCI) for sentiment classification. DCI derives term representations in a vector space common to both domains where each dimension reflects its distributional correspondence to a pivot, i.e., to a highly predictive term that behaves similarly across domains. The experiments we have conducted show that DCI obtains better performance than current state-of-the-art techniques for cross-lingual and cross-domain sentiment classification.

scholarly journals Few shot domain adaptation for in situ macromolecule structural classification in cryoelectron tomograms

2020 ◽  
Author(s):  
Liangyong Yu ◽  
Ran Li ◽  
Xiangrui Zeng ◽  
Hongyi Wang ◽  
Jie Jin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Spatial Organization ◽  
Domain Adaptation ◽  
Single Cells ◽  
Supplementary Information ◽  
Target Domain ◽  
Source Domain ◽  
Cellular Processes ◽  
Cross Domain

Abstract Motivation Cryoelectron tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at submolecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However, often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domain may perform poorly in predicting subtomogram classes in the target domain. Results In this article, we adapt a few shot domain adaptation method for deep learning-based cross-domain subtomogram classification. The essential idea of our method consists of two parts: (i) take full advantage of the distribution of plentiful unlabeled target domain data, and (ii) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods. Availability and implementation Software is available online https://github.com/xulabs/aitom. Supplementary information Supplementary data are available at Bioinformatics online.

Cross-Domain Metric and Multiple Kernel Learning Based on Information Theory

2018 ◽  
Vol 30 (3) ◽  
pp. 820-855 ◽  
Author(s):  
Wei Wang ◽  
Hao Wang ◽  
Chen Zhang ◽  
Yang Gao
Keyword(s):  
Domain Adaptation ◽  
Convex Combination ◽  
Learning Algorithms ◽  
Metric Learning ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Target Domain ◽  
Source Domain ◽  
Cross Domain ◽  
Multiple Kernel

Learning an appropriate distance metric plays a substantial role in the success of many learning machines. Conventional metric learning algorithms have limited utility when the training and test samples are drawn from related but different domains (i.e., source domain and target domain). In this letter, we propose two novel metric learning algorithms for domain adaptation in an information-theoretic setting, allowing for discriminating power transfer and standard learning machine propagation across two domains. In the first one, a cross-domain Mahalanobis distance is learned by combining three goals: reducing the distribution difference between different domains, preserving the geometry of target domain data, and aligning the geometry of source domain data with label information. Furthermore, we devote our efforts to solving complex domain adaptation problems and go beyond linear cross-domain metric learning by extending the first method to a multiple kernel learning framework. A convex combination of multiple kernels and a linear transformation are adaptively learned in a single optimization, which greatly benefits the exploration of prior knowledge and the description of data characteristics. Comprehensive experiments in three real-world applications (face recognition, text classification, and object categorization) verify that the proposed methods outperform state-of-the-art metric learning and domain adaptation methods.

scholarly journals Domain Adaptation for Pedestrian Detection Based on Prediction Consistency

2014 ◽  
Vol 2014 ◽  
pp. 1-7
Author(s):  
Yu Li-ping ◽  
Tang Huan-ling ◽  
An Zhi-yong
Keyword(s):  
Computer Vision ◽  
Detection Rate ◽  
Domain Adaptation ◽  
Learning Algorithm ◽  
Pedestrian Detection ◽  
Experimental Results ◽  
Challenging Problem ◽  
Target Domain ◽  
Source Domain ◽  
Adaptation Model

Pedestrian detection is an active area of research in computer vision. It remains a quite challenging problem in many applications where many factors cause a mismatch between source dataset used to train the pedestrian detector and samples in the target scene. In this paper, we propose a novel domain adaptation model for merging plentiful source domain samples with scared target domain samples to create a scene-specific pedestrian detector that performs as well as rich target domain simples are present. Our approach combines the boosting-based learning algorithm with an entropy-based transferability, which is derived from the prediction consistency with the source classifications, to selectively choose the samples showing positive transferability in source domains to the target domain. Experimental results show that our approach can improve the detection rate, especially with the insufficient labeled data in target scene.

A comparative study of pivot selection strategies for unsupervised cross-domain sentiment classification

2018 ◽  
Vol 33 ◽  
Author(s):  
Xia Cui ◽  
Noor Al-Bazzaz ◽  
Danushka Bollegala ◽  
Frans Coenen
Keyword(s):  
Mutual Information ◽  
Comparative Study ◽  
Domain Adaptation ◽  
Selection Strategy ◽  
Target Domain ◽  
Source Domain ◽  
Selection Strategies ◽  
Cross Domain ◽  
Pivot Selection ◽  
Pointwise Mutual Information

AbstractSelecting pivot features that connect a source domain to a target domain is an important first step in unsupervised domain adaptation (UDA). Although different strategies such as the frequency of a feature in a domain, mutual (or pointwise mutual) information have been proposed in prior work in domain adaptation (DA) for selecting pivots, a comparative study into (a) how the pivots selected using existing strategies differ, and (b) how the pivot selection strategy affects the performance of a target DA task remain unknown. In this paper, we perform a comparative study covering different strategies that use both labelled (available for the source domain only) as well as unlabelled (available for both the source and target domains) data for selecting pivots for UDA. Our experiments show that in most cases pivot selection strategies that use labelled data outperform their unlabelled counterparts, emphasising the importance of the source domain labelled data for UDA. Moreover, pointwise mutual information and frequency-based pivot selection strategies obtain the best performances in two state-of-the-art UDA methods.

scholarly journals Remote Sensing Image Retrieval with Combined Features Of Salient Region

2014 ◽  
Vol XL-6 ◽  
pp. 83-88 ◽  
Author(s):  
Z. F. Shao ◽  
W. X. Zhou ◽  
Q. M. Cheng
Keyword(s):  
Remote Sensing ◽  
Visual Attention ◽  
Image Retrieval ◽  
Texture Features ◽  
Remote Sensing Image ◽  
Experimental Results ◽  
Semantic Gap ◽  
Visual Attention Model ◽  
Attention Model ◽  
Combined Features

Low-level features tend to achieve unsatisfactory retrieval results in remote sensing image retrieval community because of the existence of semantic gap. In order to improve retrieval precision, visual attention model is used to extract salient objects from image according to their saliency. Then color and texture features are extracted from salient objects and regarded as feature vectors for image retrieval. Experimental results demonstrate that our method improves retrieval results and obtains higher precision.

scholarly journals Discriminative Sparse Filtering for Multi-Source Image Classification

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5868 ◽  
Author(s):  
Chao Han ◽  
Deyun Zhou ◽  
Zhen Yang ◽  
Yu Xie ◽  
Kai Zhang
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Source Image ◽  
Unified Framework ◽  
Target Domain ◽  
Maximum Mean Discrepancy ◽  
Source Domain ◽  
Cross Domain ◽  
Sparse Filtering ◽  
Novel Approach

Distribution mismatch caused by various resolutions, backgrounds, etc. can be easily found in multi-sensor systems. Domain adaptation attempts to reduce such domain discrepancy by means of different measurements, e.g., maximum mean discrepancy (MMD). Despite their success, such methods often fail to guarantee the separability of learned representation. To tackle this issue, we put forward a novel approach to jointly learn both domain-shared and discriminative representations. Specifically, we model the feature discrimination explicitly for two domains. Alternating discriminant optimization is proposed to obtain discriminative features with an l2 constraint in labeled source domain and sparse filtering is introduced to capture the intrinsic structures exists in the unlabeled target domain. Finally, they are integrated in a unified framework along with MMD to align domains. Extensive experiments compared with state-of-the-art methods verify the effectiveness of our method on cross-domain tasks.

Sign in / Sign up

Export Citation Format

Share Document