24 citations · 46 across the 8 of their papers we have counts for
8 papers
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detection
Konyul Park, Yecheol Kim, Junho Koh +2
Developing high-performance, real-time architectures for LiDAR-based 3D object detectors is essential for the successful commercialization of autonomous vehicles. Pillar-based meth…
MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection
Junho Koh, Junhyung Lee, Youngwoo Lee +2
Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time…
3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection
Yecheol Kim, Konyul Park, Minwook Kim +2
Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection. One key challenge in camera-LiDAR fusion involves mitigating the large d…
On Divergence Measures for Bayesian Pseudocoresets
Balhae Kim, Jungwon Choi, Seanie Lee +3
A Bayesian pseudocoreset is a small synthetic dataset for which the posterior over parameters approximates that of the original dataset. While promising, the scalability of Bayesia…
D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud Sequence
Junhyung Lee, Junho Koh, Youngwoo Lee +1
LiDAR sensors are widely used for 3D object detection in various mobile robotics applications. LiDAR sensors continuously generate point cloud data in real-time. Conventional 3D ob…
DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition
Jae Soon Baik, In Young Yoon, Jun Won Choi
There is growing interest in the challenging visual perception task of learning from long-tailed class distributions. The extreme class imbalance in the training dataset biases the…
Learning from Data with Noisy Labels Using Temporal Self-Ensemble
Jun Ho Lee, Jae Soon Baik, Tae Hwan Hwang +1
There are inevitably many mislabeled data in real-world datasets. Because deep neural networks (DNNs) have an enormous capacity to memorize noisy labels, a robust training scheme i…
ST-CoNAL: Consistency-Based Acquisition Criterion Using Temporal Self-Ensemble for Active Learning
Jae Soon Baik, In Young Yoon, Jun Won Choi
Modern deep learning has achieved great success in various fields. However, it requires the labeling of huge amounts of data, which is expensive and labor-intensive. Active learnin…