I am an associate professor of Artificial Intelligence and Computer Science at POSTECH, and a faculty member of POSTECH Computer Vision Lab. I did a post-doc with Dr. Ivan Laptev and Prof. Jean Ponce in the WILLOW team at the Department of Computer Science of the École Normale Supérieure and Inria Paris. I completed my BS and PhD at POSTECH where I worked with Prof. Joon Hee Han and Prof. Bohyung Han.

My research lies in computer vision and machine learning. I am particularly interested in developing vision models working in real-world scenarios, e.g., open-set/domain recognition, models robust against adverse conditions, and learning with limited/noisy labels or biased data.

News

2023

  I serve as an area chair of CVPR 2023, ICCV 2023, and WACV 2023.

2022

  A paper on few-shot metric learning is accepted in ACCV 2022.
  A paper on learning debiased classifiers is accepted in NeurIPS 2022.
  Two papers on domain adaptation and generalization are accepted in ECCV 2022.
  A paper on weakly supervised learning is accepted in IJCV.
  Eight papers (including one best paper finalist) are accepted in CVPR 2022.

  Our paper on foggy scene segmentation was nominated as a best paper finalist in CVPR 2022.
  Namyup, Juwon, Sungyeon, Sehyun, and Sohyun won the Qualcomm Innovation Fellowship 2022.
  Namyup and Jungwoo won the POSTECHIAN Fellowship.
  Sehyun, Sohyun, and Sungyeon won the gold prize at IPIU 2022.

  I serve as an area chair of CVPR 2022 and ACCV 2022.

  Our work on referring image segmentation is featured in MSRA Highlighted Research.
  Our work on foggy scene segmentation is featured in Donga Science.

  Our proposal (as the PI) is awarded the prestigious Samsung Science and Technology Foundation research grant.

Selected Recent Publications

Learning Debiased Classifier with Biased Committee

Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, and Suha Kwak
Conference on Neural Information Processing Systems (NeurIPS), 2022

Combating Label Distribution Shift for Active Domain Adaptation

Sehyun Hwang, Sohyun Lee, Sungyeon Kim, Jungseul Ok, and Suha Kwak
European Conference on Computer Vision (ECCV), 2022
Qualcomm Innovation Fellowship Winner

Cross-Domain Ensemble Distillation for Domain Generalization

Kyungmoon Lee, Sungyeon Kim, and Suha Kwak
European Conference on Computer Vision (ECCV), 2022

Learning to Detect Semantic Boundaries with Image-level Class Labels

Namyup Kim*, Sehyun Hwang*, and Suha Kwak (*equal contribution)
International Journal of Computer Vision (IJCV), 2022

FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation

Sohyun Lee, Taeyoung Son, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Best Paper Finalist, Oral Presentation, Qualcomm Innovation Fellowship Winner

Collaborative Transformers for Grounded Situation Recognition

Junhyeong Cho, Youngseok Yoon, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

ReSTR: Convolution-free Referring Image Segmentation Using Transformers

Namyup Kim, Dongwon Kim, Cuiling Lan, Wenjun Zeng, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Qualcomm Innovation Fellowship Winner

Self-Taught Metric Learning without Labels

Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Qualcomm Innovation Fellowship Winner

Semi-supervised Semantic Segmentation with Error Localization Network

Donghyeon Kwon and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Style Neophile: Constantly Seeking Novel Styles for Domain Generalization

Juwon Kang, Sohyun Lee, Namyup Kim, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Qualcomm Innovation Fellowship Winner

Detector-Free Weakly Supervised Group Activity Recognition

Dongkeun Kim, Jinsung Lee, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Reflection and Rotation Symmetry Detection via Equivariant Learning

Ahyun Seo, Byungjin Kim, Suha Kwak, and Minsu Cho
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Relational Self-Attention: What's Missing in Attention for Video Understanding

Manjin Kim*, Heeseung Kwon*, Chunyu Wang, Suha Kwak, and Minsu Cho (*equal contribution)
Conference on Neural Information Processing Systems (NeurIPS), 2021

ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer

Boseung Jeong*, Jicheol Park*, and Suha Kwak (*equal contribution)
IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition

Heeseung Kwon*, Manjin Kim*, Suha Kwak, and Minsu Cho (*equal contribution)
IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Embedding Transfer with Label Relaxation for Improved Metric Learning

Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

URIE: Universal Image Enhancement for Visual Recognition in the Wild

Taeyoung Son, Juwon Kang, Namyup Kim, Sunghyun Cho, and Suha Kwak
European Conference on Computer Vision (ECCV), 2020

MotionSqueeze: Neural Motion Feature Learning for Video Understanding

Heeseung Kwon, Manjin Kim, Suha Kwak, and Minsu Cho
European Conference on Computer Vision (ECCV), 2020

Proxy Anchor Loss for Deep Metric Learning

Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Deep Metric Learning Beyond Binary Supervision

Sungyeon Kim, Minkyo Seo, Ivan Laptev, Minsu Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Oral Presentation, Qualcomm Innovation Fellowship Winner

Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations

Jiwoon Ahn, Sunghyun Cho, and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Oral Presentation

Domain Specific Batch Normalization for Unsupervised Domain Adaptation

Woong-Gi Chang*, Tackgeun You*, Seonguk Seo*, Suha Kwak, and Bohyung Han (*equal contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation

Jiwoon Ahn and Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Professional Service

 Editorial Board Member
  • International Journal of Computer Vision (IJCV), 2021 ~ present
 Area Chair / Senior Program Committee
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, 2023
  • IEEE/CVF International Conference on Computer Vision (ICCV), 2019, 2021
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
  • Asian Conference on Computer Vision (ACCV), 2022
  • International Conference on Machine Vision Applications (MVA), 2021

Contact

+82-54-279-2390
315 B2, POSTECH

77 Cheongam-ro, Nam-gu
Pohang, Gyungbuk
37673 Korea

suha.kwak (a) postech.ac.kr