1 code implementation • 20 Mar 2024 • Joonmyung Choi, Sanghyeok Lee, Jaewon Chu, Minhyuk Choi, Hyunwoo J. Kim
To tackle these issues, we propose training free token merging for lightweight video Transformer (vid-TLDR) that aims to enhance the efficiency of video Transformers by merging the background tokens without additional training.
Ranked #2 on Video Retrieval on SSv2-template retrieval (using extra training data)
1 code implementation • 15 Mar 2024 • Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim
Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss.
Ranked #1 on Efficient ViTs on ImageNet-1K (With LV-ViT-S)
1 code implementation • ICCV 2023 • Dongjun Lee, Seokwon Song, Jihee Suh, Joonmyung Choi, Sanghyeok Lee, Hyunwoo J. Kim
RPO leverages masked attention to prevent the internal representation shift in the pre-trained model.
Ranked #6 on Prompt Engineering on Caltech-101
1 code implementation • CVPR 2023 • Jinyoung Park, Sanghyeok Lee, Sihyeon Kim, Yunyang Xiong, Hyunwoo J. Kim
In this paper, we present a Self-Positioning point-based Transformer (SPoTr), which is designed to capture both local and global shape contexts with reduced complexity.
Ranked #2 on 3D Part Segmentation on ShapeNet-Part
1 code implementation • 13 Oct 2022 • Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim
Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity.
Ranked #40 on 3D Part Segmentation on ShapeNet-Part
no code implementations • 25 Nov 2021 • Myoung-jae Lee, Sanghyeok Lee
We evaluate DD and the related approaches with simulation and empirical studies, and recommend 'Poisson Quasi-MLE' for non-negative (such as count or zero-censored) Y and (multinomial) logit MLE for binary, fractional or multinomial Y.
1 code implementation • ICCV 2021 • Sihyeon Kim, Sanghyeok Lee, Dasol Hwang, Jaewon Lee, Seong Jae Hwang, Hyunwoo J. Kim
Although data augmentation is a standard approach to compensate for the scarcity of data, it has been less explored in the point cloud literature.
Ranked #11 on Point Cloud Classification on PointCloud-C