Extensive experiments are conducted to demonstrate the power of our new datasets in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model.
Secondly, we propose the Prototypical Adversarial Domain Adaptation (PADA) model which utilizes unlabeled bridge domains to align feature distribution between source and target with a large discrepancy.
In this work, we present a principled approach to the problem of federated domain adaptation, which aims to align the representations learned among the different nodes with the data distribution of the target node.
In this paper, we explore the task of Generalized Domain Adaptation (GDA): How to transfer knowledge across different domains in the presence of both covariate and label shift?
Unsupervised model transfer has the potential to greatly improve the generalizability of deep models to novel domains.
Ranked #3 on Multi-target Domain Adaptation on DomainNet
Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain.
This paper proposes an approach to domain transfer based on a pairwise loss function that helps transfer control policies learned in simulation onto a real robot.
In this paper, we present a new large-scale benchmark called Syn2Real, which consists of a synthetic domain rendered from 3D object models and two real-image domains containing the same object categories.
We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains.
Experimentally, we show training off-the-shelf classifiers on the newly generated data can significantly boost performance when testing on the real image domains (PASCAL VOC 2007 benchmark and Office dataset), improving upon several existing methods.
We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results.
We address the difficult problem of distinguishing fine-grained object categories in low resolution images.
Deep convolutional neural networks learn extremely powerful image representations, yet most of that power is hidden in the millions of deep-layer parameters.
Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category. We show that augmenting the training data of contemporary Deep Convolutional Neural Net (DCNN) models with such synthetic data can be effective, especially when real training data is limited or not well matched to the target domain.