574 citations · 1k across the 14 of their papers we have counts for
14 papers
Network Architecture Search for Domain Adaptation
Yichen Li, Xingchao Peng
Deep networks have been used to learn transferable representations for domain adaptation. Existing deep domain adaptation methods systematically employ popular hand-crafted network…
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
Xingchao Peng, Yichen Li, Kate Saenko
Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distr…
Learning Domain Adaptive Features with Unlabeled Domain Bridges
Yichen Li, Xingchao Peng
Conventional cross-domain image-to-image translation or unsupervised domain adaptation methods assume that the source domain and target domain are closely related. This neglects a…
Federated Adversarial Domain Adaptation
Xingchao Peng, Zijun Huang, Yizhe Zhu +1
Federated learning improves data privacy and efficiency in machine learning performed over networks of distributed devices, such as mobile phones, IoT and wearable devices, etc. Ye…
Class-imbalanced Domain Adaptation: An Empirical Odyssey
Shuhan Tan, Xingchao Peng, Kate Saenko
Unsupervised domain adaptation is a promising way to generalize deep models to novel domains. However, the current literature assumes that the label distribution is domain-invarian…
Domain Agnostic Learning with Disentangled Representations
Xingchao Peng, Zijun Huang, Ximeng Sun +1
Unsupervised model transfer has the potential to greatly improve the generalizability of deep models to novel domains. Yet the current literature assumes that the separation of tar…
Moment Matching for Multi-Source Domain Adaptation
Xingchao Peng, Qinxun Bai, Xide Xia +3
Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are col…
Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
Xingchao Peng, Ben Usman, Kuniaki Saito +3
Unsupervised transfer of object recognition models from synthetic to real data is an important problem with many potential applications. The challenge is how to "adapt" a model tra…
VisDA: The Visual Domain Adaptation Challenge
Xingchao Peng, Ben Usman, Neela Kaushik +3
We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains. Unsupervised domain adap…
Synthetic to Real Adaptation with Generative Correlation Alignment Networks
Xingchao Peng, Kate Saenko
Synthetic images rendered from 3D CAD models are useful for augmenting training data for object recognition algorithms. However, the generated images are non-photorealistic and do…
Combining Texture and Shape Cues for Object Recognition With Minimal Supervision
Xingchao Peng, Kate Saenko
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 free…
Fine-to-coarse Knowledge Transfer For Low-Res Image Classification
Xingchao Peng, Judy Hoffman, Stella X. Yu +1
We address the difficult problem of distinguishing fine-grained object categories in low resolution images. Wepropose a simple an effective deep learning approach that transfers fi…
What Do Deep CNNs Learn About Objects?
Xingchao Peng, Baochen Sun, Karim Ali +1
Deep convolutional neural networks learn extremely powerful image representations, yet most of that power is hidden in the millions of deep-layer parameters. What exactly do these…
Learning Deep Object Detectors from 3D Models
Xingchao Peng, Baochen Sun, Karim Ali +1
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 aug…