Xingchao Peng

Research Assistant
Boston University
Email: xpeng@bu.edu

CV Google Scholar

About Me

My research interest focuses on transfer learning and domain adaptation, especially for transfer learning between synthetic domain and realistic domain. I am currently a research assistant at Boston University, advised by Prof. Kate Saenko.

I graduated from Peking University with a B.S. in Computer Science in June 2013, working with Prof. Yuxin Peng. I have spent summers at ICSI, working with Dr. Stella Yu and Prof. Trevor Darrell.

Publications

Synthetic to Real Adaptation with Generative Correlation Alignment Networks
In this work, we propose a Deep Generative Alignment Network (DGCAN) to synthesize images. DGCAN leverages a shape loss and a low level statistic matching loss to minimize the domain discrepancy between synthetic and real images deep feature space. 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).
Xingchao Peng, Kate Saenko
WACV 2018
Ground2sky Label Transfer for Fine-grained Aerial Car Recognition
We propose a novel solution to collect fine-grained annotations of aerial images and develop the first ground-to-sky cross-view car dataset with instance-level correspondences. We compare the performance of human experts and deep learning approaches on fine-grained car recognition from aerial imagery. We further show that with simple data augmentation, a classifier can be trained from fewer instances yet achieves comparable or even significantly better performance than human.
Baochen Sun, Xingchao Peng, Stella X Yu, Kate Saenko
ICIP 2017 (Oral)
Combining Texture and Shape Cues for Object Recognition with Minimal Supervision
We propose a two-stream deep learning framework that combines shape and texture cues seperately, with one stream learning visual texture cues from image search data, and the other stream learning rich shape information from 3D CAD models. Our method outperforms previous web image based models, 3D CAD model based approaches, and weakly supervised learning.
Xingchao Peng, Kate Saenko
ACCV 2016
Fine-to-Coarse Knowledge Transfer for Low-Res Image Classification
We propose 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
Xingchao Peng, Judy Hoffman, Stella X Yu, Kate Saenko
ICIP 2016
Learning Deep Object Detectors from 3D Models
We propose 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
Xingchao Peng, Baochen Sun, Karim Ali, Kate Saenko
ICCV 2015