Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning


Nov 21, 2021
Yunsung Lee, Teakgyu Hong, Han-Cheol Cho, Junbum Cha, Seungryong Kim

* Accepted to ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Semantic Correspondence with Transformers


Jun 04, 2021
Seokju Cho, Sunghwan Hong, Sangryul Jeon, Yunsung Lee, Kwanghoon Sohn, Seungryong Kim

* Code and trained models will be made available at https://github.com/SunghwanHong/CATs 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts


Feb 17, 2021
Junbum Cha, Hancheol Cho, Kyungjae Lee, Seunghyun Park, Yunsung Lee, Sungrae Park


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Long-Term Object Tracking via Improved Discriminative Model Prediction


Aug 25, 2020
Seokeon Choi, Junhyun Lee, Yunsung Lee, Alexander Hauptmann

* Accepted to ECCV 2020 Workshop 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence


May 11, 2020
Junsoo Lee, Eungyeup Kim, Yunsung Lee, Dongjun Kim, Jaehyuk Chang, Jaegul Choo

* Accepted to CVPR 2020 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email