Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Xingchao Peng is active.

Publication


Featured researches published by Xingchao Peng.


international conference on computer vision | 2015

Learning Deep Object Detectors from 3D Models

Xingchao Peng; Baochen Sun; Karim Ali; Kate Saenko

Crowdsourced 3D CAD models are 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. Most freely available CAD models capture 3D shape but are often missing other low level cues, such as realistic object texture, pose, or background. In a detailed analysis, we use synthetic CAD images to probe the ability of DCNN to learn without these cues, with surprising findings. In particular, we show that when the DCNN is fine-tuned on the target detection task, it exhibits a large degree of invariance to missing low-level cues, but, when pretrained on generic ImageNet classification, it learns better when the low-level cues are simulated. We show that our synthetic DCNN training approach significantly outperforms previous methods on the benchmark PASCAL VOC2007 dataset when learning in the few-shot scenario and improves performance in a domain shift scenario on the Office benchmark.


international conference on image processing | 2016

Fine-to-coarse knowledge transfer for low-res image classification

Xingchao Peng; Judy Hoffman; Stella X. Yu; Kate Saenko

We address the difficult problem of distinguishing fine-grained object categories in low resolution images. We propose a simple an effective deep learning approach that transfers fine-grained knowledge gained from high resolution training data to the coarse low-resolution test scenario. Such fine-to-coarse knowledge transfer has many real world applications, such as identifying objects in surveillance photos or satellite images where the image resolution at the test time is very low but plenty of high resolution photos of similar objects are available. Our extensive experiments on two standard benchmark datasets containing fine-grained car models and bird species demonstrate that our approach can effectively transfer fine-detail knowledge to coarse-detail imagery.


asian conference on computer vision | 2016

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 freely available unlabeled web search results. The explosion of visual data on the web can potentially make visual examples of almost any object easily accessible via web search. Previous unsupervised methods have utilized either large scale sources of texture cues from the web, or shape information from data such as crowdsourced CAD models. We propose a two-stream deep learning framework that combines these cues, with one stream learning visual texture cues from image search data, and the other stream learning rich shape information from 3D CAD models. To perform classification or detection for a novel image, the predictions of the two streams are combined using a late fusion scheme. We present experiments and visualizations for both tasks on the standard benchmark PASCAL VOC 2007 to demonstrate that texture and shape provide complementary information in our model. Our method outperforms previous web image based models, 3D CAD model based approaches, and weakly supervised models.


arXiv: Computer Vision and Pattern Recognition | 2014

Exploring Invariances in Deep Convolutional Neural Networks Using Synthetic Images.

Xingchao Peng; Baochen Sun; Karim Ali; Kate Saenko


workshop on applications of computer vision | 2018

Synthetic to Real Adaptation with Generative Correlation Alignment Networks

Xingchao Peng; Kate Saenko


arXiv: Computer Vision and Pattern Recognition | 2015

Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments.

Eric Tzeng; Coline Devin; Judy Hoffman; Chelsea Finn; Xingchao Peng; Sergey Levine; Kate Saenko; Trevor Darrell


arXiv: Computer Vision and Pattern Recognition | 2017

VisDA: The Visual Domain Adaptation Challenge.

Xingchao Peng; Ben Usman; Neela Kaushik; Judy Hoffman; Dequan Wang; Kate Saenko


arXiv: Computer Vision and Pattern Recognition | 2015

What Do Deep CNNs Learn About Objects

Xingchao Peng; Baochen Sun; Karim Ali; Kate Saenko


computer vision and pattern recognition | 2018

VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation

Xingchao Peng; Ben Usman; Neela Kaushik; Dequan Wang; Judy Hoffman; Kate Saenko


Archive | 2018

Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation.

Xingchao Peng; Ben Usman; Kuniaki Saito; Neela Kaushik; Judy Hoffman; Kate Saenko

Collaboration


Dive into the Xingchao Peng's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Baochen Sun

University of Massachusetts Lowell

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Karim Ali

École Polytechnique Fédérale de Lausanne

View shared research outputs
Top Co-Authors

Avatar

Dequan Wang

University of California

View shared research outputs
Top Co-Authors

Avatar

Stella X. Yu

University of California

View shared research outputs
Top Co-Authors

Avatar

Chelsea Finn

University of California

View shared research outputs
Top Co-Authors

Avatar

Coline Devin

University of California

View shared research outputs
Top Co-Authors

Avatar

Eric Tzeng

University of California

View shared research outputs
Researchain Logo
Decentralizing Knowledge