1 code implementation • 24 Apr 2024 • Eunsu Baek, Keondo Park, Jiyoon Kim, Hyung-Sin Kim
We find that existing OOD detection methods do not cope with the covariate shifts in ImageNet-ES, implying that the definition and detection of OOD should be revisited to embrace real-world distribution shifts.
no code implementations • 6 Sep 2023 • You Rim Choi, Gyeongseon Eo, Wonhyuck Youn, Hyojin Lee, Haemin Jang, Dongyoon Kim, Hyunwoo Shin, Hyung-Sin Kim
Recognizing that sleep videos exhibit minimal motion, this work investigates the fundamental question: "Are respiratory events adequately reflected in human motions during sleep?"
no code implementations • ICCV 2023 • Sunwook Hwang, Youngseok Kim, Seongwon Kim, Saewoong Bahk, Hyung-Sin Kim
In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional raw-level point cloud: learning from unlabeled de-identified intermediate features (i. e., smashed data) to preserve privacy.
1 code implementation • 20 Jul 2022 • Jiseok Youn, Jaehun Song, Hyung-Sin Kim, Saewoong Bahk
By comparing their performance to (bitwidth-dedicated) QAT, existing bitwidth adaptive QAT and vanilla meta-learning, we find that merging bitwidths into meta-learning tasks achieves a higher level of robustness.
1 code implementation • 27 May 2022 • Woojung Kim, Keondo Park, Kihyuk Sohn, Raphael Shu, Hyung-Sin Kim
Compared to a FSSL approach based on weight sharing, the prototype-based inter-client knowledge sharing significantly reduces both communication and computation costs, enabling more frequent knowledge sharing between more clients for better accuracy.
1 code implementation • 23 May 2022 • Jaehun Song, Min-hwan Oh, Hyung-Sin Kim
Personalized Federated Learning (FL) is an emerging research field in FL that learns an easily adaptable global model in the presence of data heterogeneity among clients.