I am a PhD candidate in the College of Information and Computer Sciences at Umass-Amherst. I am in the computer vision lab and my advisor is Subhransu Maji. My research focuses on typical vision tasks under the circumstances of limited training data, including the fields of domain adaptation, few-shot learning, fine-grained classification, semi-supervised learning and self-supervised learning. Here is my CV.

Challenges

Second Semi-Supervised Challenge on iNaturalist at FGVC 8 at CVPR 2021 (Semi-iNat)

Kaggle, github page

First Semi-Supervised Challenge on iNaturalist at FGVC 7 at CVPR 2020 (Semi-Aves)

Kaggle, github page

Preprints

Unsupervised Discovery of Object Landmarks via Contrastive Learning

Zezhou Cheng, Jong-Chyi Su, Subhransu Maji
arXiv, 6/26/2020
arXiv, project page, github

Semi-Supervised Fine-Grained Recognition Challenge at FGVC7

Jong-Chyi Su, Subhransu Maji
arXiv, 3/11/2021
arXiv

Publications

A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification

Jong-Chyi Su, Zezhou Cheng, Subhransu Maji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (oral), 2021
arXiv

When Does Self-supervision Improve Few-shot Learning?

Jong-Chyi Su, Subhransu Maji, Bharath Hariharan
European Conference on Computer Vision (ECCV), 2020
arXiv, project page, github, slides

Active Adversarial Domain Adaptation

Jong-Chyi Su, Yi-Hsuan Tsai, Kihyuk Sohn, Buyu Liu, Subhransu Maji, Manmohan Chandraker
Winter Conference on Applications of Computer Vision (WACV), 2020
arXiv

A Deeper Look at 3D Shape Classifiers

Jong-Chyi Su, Matheus Gadelha, Rui Wang, Subhransu Maji
Second Workshop on 3D Reconstruction Meets Semantics at ECCV, 2018
arXiv, project page/dataset, pdf, mvcnn code in PyTorch

Reasoning about Fine-grained Attribute Phrases using Reference Games

Jong-Chyi Su*, Chenyun Wu*, Huaizu Jiang, Subhransu Maji
International Conference on Computer Vision (ICCV), 2017
arXiv, project page, pdf, dataset and code in Tensorflow

Adapting Models to Signal Degradation using Distillation

Jong-Chyi Su, Subhransu Maji
British Machine Vision Conference (BMVC), 2017
arXiv, project page, pdf, code in matconvnet

Depth Estimation and Specular Removal for Glossy Surfaces Using Point and Line Consistency with Light-Field Cameras

Michael Tao, Jong-Chyi Su, Ting-Chun Wang, Jitendra Malik, and Ravi Ramamoorthi
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Volume 38 Issue 6, June 2016
pdf, code/dataset

Misc

Music that I play