Universal Domain Adaptation

You, Kaichao; Long, Mingsheng; Cao, Zhangjie; Wang, Jianmin; Jordan, Michael I.

doi:10.1109/cvpr.2019.00283

Cited by 332 publications

(268 citation statements)

References 26 publications

Supporting

Mentioning

267

Contrasting

Order By: Relevance

“…Since the majority of the studied baselines cannot use the continuous log (IC50) values in the source domain, binarized log (IC50) labels provided by ( Iorio et al , 2016 ) using the Waterfall approach ( Barretina et al , 2012 ) were used to train them. Finally, for the minimax optimization, a gradient reversal layer was employed by AITL and the adversarial baselines ( Ganin et al , 2016 ) which is a well-established approach in domain adaptation ( Long et al , 2018 ; You et al , 2019 ; Zhang et al , 2019 ).…”

Section: Resultsmentioning

confidence: 99%

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

et al. 2020

View full text Add to dashboard Cite

Motivation The goal of pharmacogenomics is to predict drug response in patients using their single- or multi-omics data. A major challenge is that clinical data (i.e. patients) with drug response outcome is very limited, creating a need for transfer learning to bridge the gap between large pre-clinical pharmacogenomics datasets (e.g. cancer cell lines), as a source domain, and clinical datasets as a target domain. Two major discrepancies exist between pre-clinical and clinical datasets: (i) in the input space, the gene expression data due to difference in the basic biology, and (ii) in the output space, the different measures of the drug response. Therefore, training a computational model on cell lines and testing it on patients violates the i.i.d assumption that train and test data are from the same distribution. Results We propose Adversarial Inductive Transfer Learning (AITL), a deep neural network method for addressing discrepancies in input and output space between the pre-clinical and clinical datasets. AITL takes gene expression of patients and cell lines as the input, employs adversarial domain adaptation and multi-task learning to address these discrepancies, and predicts the drug response as the output. To the best of our knowledge, AITL is the first adversarial inductive transfer learning method to address both input and output discrepancies. Experimental results indicate that AITL outperforms state-of-the-art pharmacogenomics and transfer learning baselines and may guide precision oncology more accurately. Availability and implementation https://github.com/hosseinshn/AITL. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Resultsmentioning

confidence: 99%

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In addition, through improving single domain discriminator into multiple domain discriminators, the features of different levels [26] and the features of different classes [27][28] can be aligned more accurately, and the domain discriminator can be also designed based on two-level domain confusion scheme [29]. The method is still effective when the number of classes in the source domain is more than in the target domains [30][31], and the number of classes in the target domain is more than in the source domains [32].…”

Section: Related Workmentioning

confidence: 99%

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Jia

Sun

2020

IEEE Access

View full text Add to dashboard Cite

Although most transfer learning methods can reduce the difference of the feature distributions between the source and target domains effectively, some classes in the two domains may still be misaligned after domain adaptation, especially for the classes with similar features such as "bicycle" and "motorcycle". Therefore, a graph regularization based adversarial network model is proposed, whose innovations mainly include the following two aspects: First, a constraint function which is used to measure the difference between the features belonged to different classes is proposed, whose purpose is that not only the training accuracy is taken into account during supervised training, but also the difference between classes should be enlarged as much as possible; Then, a graph regularization constraint function is proposed, which makes all the classes have good local preserving properties after domain adaptation, and further reduces the possibility of all classes being misaligned. Experimental results on several cross-domain benchmark datasets show that our newly proposed approach outperforms state of the art methods.

show abstract

“…To minimise the covariate shift, several approaches have been proposed, such as Maximum Mean Discrepancy (MMD) [3], adversarial training [4][5][6][7], as well as styletransfer [8]. DA has recently been mostly investigated for classification tasks, showing outstanding results on closed set [5,7,[9][10][11], open set [12,13], partial [14,15], and even universal cases [16]. However, regression tasks have attracted less attention in the computer vision community.…”

Section: Introductionmentioning

confidence: 99%

“…Examples of holistic regression applications are counting [17,18], age estimation [19], and time series forecasting [20]. Domain adaptation for holistic regression is more prone to label gap, i.e., the target dataset may contain values that are not contained in the source dataset (in [16], this is referred to as category gap; we use the term label gap to be more generic to accommodate our application). This phenomenon is depicted in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap

et al. 2021

View full text Add to dashboard Cite

This paper proposes a novel approach for semi-supervised domain adaptation for holistic regression tasks, where a DNN predicts a continuous value y∈R given an input image x. The current literature generally lacks specific domain adaptation approaches for this task, as most of them mostly focus on classification. In the context of holistic regression, most of the real-world datasets not only exhibit a covariate (or domain) shift, but also a label gap—the target dataset may contain labels not included in the source dataset (and vice versa). We propose an approach tackling both covariate and label gap in a unified training framework. Specifically, a Generative Adversarial Network (GAN) is used to reduce covariate shift, and label gap is mitigated via label normalisation. To avoid overfitting, we propose a stopping criterion that simultaneously takes advantage of the Maximum Mean Discrepancy and the GAN Global Optimality condition. To restore the original label range—that was previously normalised—a handful of annotated images from the target domain are used. Our experimental results, run on 3 different datasets, demonstrate that our approach drastically outperforms the state-of-the-art across the board. Specifically, for the cell counting problem, the mean squared error (MSE) is reduced from 759 to 5.62; in the case of the pedestrian dataset, our approach lowered the MSE from 131 to 1.47. For the last experimental setup, we borrowed a task from plant biology, i.e., counting the number of leaves in a plant, and we ran two series of experiments, showing the MSE is reduced from 2.36 to 0.88 (intra-species), and from 1.48 to 0.6 (inter-species).

show abstract

Universal Domain Adaptation

Cited by 332 publications

References 26 publications

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap

Contact Info

Product

Resources

About