False Positive Sampling-based Data Augmentation for Enhanced 3D Object Detection Accuracy

no code implementations • 5 Mar 2024 • Jiyong Oh, Junhaeng Lee, Woongchan Byun, Minsang Kong, Sang Hun Lee

Therefore, this study aims to overcome the limitations of ground-truth sampling and improve the performance of 3D object detection models by developing a new augmentation technique called false-positive sampling.

3D Object Detection Data Augmentation +2

SBNet: Segmentation-based Network for Natural Language-based Vehicle Search

no code implementations • 22 Apr 2021 • Sangrok Lee, Taekang Woo, Sang Hun Lee

Natural language-based vehicle retrieval is a task to find a target vehicle within a given image based on a natural language description as a query.

Future prediction Retrieval

Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification

no code implementations • 21 Apr 2021 • Sangrok Lee, Taekang Woo, Sang Hun Lee

Meanwhile, based on the researchers' insights, various handcrafted multi-attention architectures for specific viewpoints or vehicle parts have been proposed.

Vehicle Re-Identification

StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification

no code implementations • 25 Apr 2020 • Sangrok Lee, Eunsoo Park, Hongsuk Yi, Sang Hun Lee

Vehicle re-identification aims to obtain the same vehicles from vehicle images.

Domain Adaptation Vehicle Re-Identification