Tsung-Wei Ke

I am a PhD student of VS program at UC Berkeley. I am advised by Dr. Stella Yu. I'm interested in computer vision, machine learning and vision science. I had been working with Dr. Tyng-Luh Liu at the Computer Vision Lab in Academia Sinica for two years after graduating from NTU with a Bachelor of Chemical Engineering.

Contact

twke@berkeley.edu

  • One paper accepted to ICLR 2021
    • Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Publications


Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Tsung-Wei Ke, Jyh-Jing Hwang, and Stella X. Yu
ICLR 2021


Adversarial Structure Matching for Structured Prediction Tasks

Jyh-Jing Hwang, Tsung-Wei Ke, Jianbo Shi and Stella X. Yu
CVPR 2019


Adaptive Affinity Field for Semantic Segmentation

Tsung-Wei Ke*, Jyh-Jing Hwang*, Ziwei Liu and Stella X. Yu (*equal contribution)
ECCV 2018


Mooney Face Classification And Prediction By Learning Across Tone

Tsung-Wei Ke, Stella X. Yu and David Whitney
ICIP 2017 (oral)


Neural MultiGrid

Tsung-Wei Ke, Michael Maire, and Stella X. Yu
arXiv:1611.07661; CVPR 2017


Variational Convolutional Networks for Human-Centric Annotations

Tsung-Wei Ke, Che-Wei Lin, Tyng-Luh Liu and Davi Geiger
ACCV 2016 (oral)


Implicit Sparse Code Hashing

Tsung-Yu Lin, Tsung-Wei Ke, and Tyng-Luh Liu.
arXiv:1512.00130