Taeckyung Lee
@taeckyung_lee
Followers
35
Following
30
Media
3
Statuses
10
Ph.D. Student @ KAIST (Advisor: Prof. Sung-Ju Lee). Collaborating with Prof. Jinwoo Shin (KAIST) and Prof. Taesik Gong (UNIST).
Joined September 2023
We're happy to announce that our work on test-time adaptation with binary feedback has been accepted to #ICML2025!. We will discuss how we can utilize human feedback for TTA. Special thanks to collaborators.@sornswgn @JunsuKim97 @jinwoos0417 @Taesik_MobileAI @wewantsj !!
1
2
9
You can now check our paper! We are hosting a poster session from 11:00 a.m. to 1:30 p.m. on July 17th. Please feel free to reach out to me to connect at ICML in Vancouver. - Arxiv: - Openreview:
openreview.net
Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using...
We're happy to announce that our work on test-time adaptation with binary feedback has been accepted to #ICML2025!. We will discuss how we can utilize human feedback for TTA. Special thanks to collaborators.@sornswgn @JunsuKim97 @jinwoos0417 @Taesik_MobileAI @wewantsj !!
0
0
5
@sornswgn @JunsuKim97 @jinwoos0417 @Taesik_MobileAI @wewantsj Please stay tuned for our camera-ready version!!
0
0
0
0
0
0
If you are attending CVPR next week, join us at our poster session!.🗓️ Fri 21 June, 17:15 - 18:45.📍 Poster Session 6 & Exhibit Hall (Arch 4A-E). (2/3).
1
0
0
Curious about *estimating test-time adaptation (TTA) accuracy* without labeled data or source data access? Check out our #CVPR2024 paper on AETTA, a novel method for TTA accuracy estimation. 📄 Paper: 💻 Code: (1/3)
1
2
4
RT @ori_press: Entropy minimization is often used to increase the accuracy of models on unlabeled data, but it isn’t clear why it works. In….
0
63
0
See you at CVPR '24!.
📄 Thrilled to announce that our research, "ATTA: Label-Free Accuracy Estimation for Test-Time Adaptation," has been accepted at #CVPR2024! Kudos to the awesome team: @taeckyung_lee, @sornswgn, and @wewantsj 👏. Stay tuned for our camera-ready version and code!
0
0
1
RT @Taesik_MobileAI: Excited to announce that our research on robust test-time adaptation for noisy streams has been accepted at #NeurIPS20….
0
3
0