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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Similarity of Neural Architectures Based on Input Gradient Transferability


Oct 20, 2022
Jaehui Hwang, Dongyoon Han, Byeongho Heo, Song Park, Sanghyuk Chun, Jong-Seok Lee

Add code

* 21pages, 10 figures, 1.5MB 

   Access Paper or Ask Questions

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

Scratching Visual Transformer's Back with Uniform Attention


Oct 16, 2022
Nam Hyeon-Woo, Kim Yu-Ji, Byeongho Heo, Dongyoon Han, Seong Joon Oh, Tae-Hyun Oh

Add code


   Access Paper or Ask Questions

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

Time Is MattEr: Temporal Self-supervision for Video Transformers


Jul 19, 2022
Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha, Jinwoo Shin

Add code

* Accepted to ICML 2022. Code is available at https://github.com/alinlab/temporal-selfsupervision 

   Access Paper or Ask Questions

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

Loss-based Sequential Learning for Active Domain Adaptation


Apr 25, 2022
Kyeongtak Han, Youngeun Kim, Dongyoon Han, Sungeun Hong

Add code

* 11 pages, 7 figures, 7 tables 

   Access Paper or Ask Questions

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

An Extendable, Efficient and Effective Transformer-based Object Detector


Apr 17, 2022
Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang

Add code

* An extension of the ICLR paper, ViDT: An Efficient and Effective Fully Transformer-based Object Detector. arXiv admin note: substantial text overlap with arXiv:2110.03921 

   Access Paper or Ask Questions

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

Spatiotemporal Augmentation on Selective Frequencies for Video Representation Learning


Apr 08, 2022
Jinhyung Kim, Taeoh Kim, Minho Shim, Dongyoon Han, Dongyoon Wee, Junmo Kim

Add code


   Access Paper or Ask Questions

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

Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?


Mar 28, 2022
Jisoo Mok, Byunggook Na, Ji-Hoon Kim, Dongyoon Han, Sungroh Yoon

Add code

* CVPR 2022 

   Access Paper or Ask Questions

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

Learning Features with Parameter-Free Layers


Feb 06, 2022
Dongyoon Han, YoungJoon Yoo, Beomyoung Kim, Byeongho Heo

Add code

* ICLR 2022 

   Access Paper or Ask Questions

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

Contrastive Vicinal Space for Unsupervised Domain Adaptation


Dec 05, 2021
Jaemin Na, Dongyoon Han, Hyung Jin Chang, Wonjun Hwang

Add code

* 10 pages, 7 figures, 5 tables 

   Access Paper or Ask Questions

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

Donut: Document Understanding Transformer without OCR


Nov 30, 2021
Geewook Kim, Teakgyu Hong, Moonbin Yim, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park

Add code

* 12 pages, 6 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
>>