no code implementations • 30 Apr 2024 • Junghyup Lee, Dohyung Kim, Jeimin Jeon, Bumsub Ham
It is thus difficult to control the degree of changes for quantized weights by scheduling the LR manually.
no code implementations • 28 Mar 2024 • Junghyup Lee, Bumsub Ham
To address this issue, we propose AZ-NAS, a novel approach that leverages the ensemble of various zero-cost proxies to enhance the correlation between a predicted ranking of networks and the ground truth substantially in terms of the performance.
no code implementations • ICCV 2023 • Jongyoun Noh, Hyekang Park, Junghyup Lee, Bumsub Ham
In this paper, we present RankMixup, a novel mixup-based framework alleviating the problem of the mixture of labels for network calibration.
no code implementations • 12 Oct 2022 • Donghyeon Baek, Youngmin Oh, SangHoon Lee, Junghyup Lee, Bumsub Ham
We introduce a CISS framework that alleviates the forgetting problem and facilitates learning novel classes effectively.
Class-Incremental Semantic Segmentation Knowledge Distillation
1 code implementation • 21 Jul 2022 • SangHoon Lee, Youngmin Oh, Donghyeon Baek, Junghyup Lee, Bumsub Ham
To this end, we introduce a novel normalization layer, dubbed ProtoNorm, that calibrates features from pedestrian proposals, while considering a long-tail distribution of person IDs, enabling L2 normalized person representations to be discriminative.
1 code implementation • ICCV 2021 • Chanho Eom, Geon Lee, Junghyup Lee, Bumsub Ham
Spatial and temporal distractors in person videos, such as background clutter and partial occlusions over frames, respectively, make this task much more challenging than image-based person reID.
Ranked #8 on Person Re-Identification on MARS
1 code implementation • ICCV 2021 • Hyunjong Park, SangHoon Lee, Junghyup Lee, Bumsub Ham
We address the problem of visible-infrared person re-identification (VI-reID), that is, retrieving a set of person images, captured by visible or infrared cameras, in a cross-modal setting.
no code implementations • ICCV 2021 • Dohyung Kim, Junghyup Lee, Bumsub Ham
This alleviates the gradient mismatch, but causes a quantizer gap problem.
1 code implementation • CVPR 2021 • Junghyup Lee, Dohyung Kim, Bumsub Ham
Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources.
no code implementations • ECCV 2020 • Wonkyung Lee, Junghyup Lee, Dohyung Kim, Bumsub Ham
The student and the decoder in the teacher, having the same network architecture as FSRCNN, try to reconstruct HR images.
no code implementations • 29 Nov 2019 • Junghyup Lee, Dohyung Kim, Wonkyung Lee, Jean Ponce, Bumsub Ham
We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category.
no code implementations • CVPR 2019 • Junghyup Lee, Dohyung Kim, Jean Ponce, Bumsub Ham
We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category.