Five papers got accepted to CVPR-20!

Five papers from the KAIST Graduate School of AI got accepted to the IEEE Conference on Computer Vision and Pattern Recognition (CVPR-20).
CVPR is one of the top conferences in Computer Vision. In 2020, it will take place at The Washington State Convention Center in Seattle, WA, from June 16 to June 20.

List of the papers:

“Regularizing Class-wise Predictions via Self-knowledge Distillation”
by Sukmin Yun*, Jongjin Park* (KAIST AI), Kimin Lee, and Jinwoo Shin (KAIST AI)

“M2m: Imbalanced Classification via Major-to-minor Translation”
by Jaehyung Kim*, Jongheon Jeong*, and Jinwoo Shin (KAIST AI)

“Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks”
by Sungha Choi, Joanne Kim, and Jaegul Choo (KAIST AI, as of 3/1/2020)

“Reference-based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence”
by Junsoo Lee, Eungyeup Kim, Yunsung Lee, Dongjun Kim, Jaehyuk Chang, and Jaegul Choo (KAIST AI, as of 3/1/2020)

“Exploring Unlabeled Faces for Novel Attribute Discovery”
by Hyojin Bahng, Sunghyo Chung, Seungjoo Yoo, and Jaegul Choo (KAIST AI, as of 3/1/2020)