2 citations · 3 across the 7 of their papers we have counts for
7 papers
LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation
Amirreza Shaban, JoonHo Lee, Sanghun Jung +2
We introduce LiDAR-UDA, a novel two-stage self-training-based Unsupervised Domain Adaptation (UDA) method for LiDAR segmentation. Existing self-training methods use a model trained…
Improving Evaluation of Debiasing in Image Classification
Jungsoo Lee, Juyoung Lee, Sanghun Jung +1
Image classifiers often rely overly on peripheral attributes that have a strong correlation with the target class (i.e., dataset bias) when making predictions. Due to the dataset b…
CAFA: Class-Aware Feature Alignment for Test-Time Adaptation
Sanghun Jung, Jungsoo Lee, Nanhee Kim +3
Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-ti…
3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations
Minsoo Lee, Chaeyeon Chung, Hojun Cho +4
While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications. Due to their view-dependent and ligh…
CG-NeRF: Conditional Generative Neural Radiance Fields
Kyungmin Jo, Gyumin Shim, Sanghun Jung +2
While recent NeRF-based generative models achieve the generation of diverse 3D-aware images, these approaches have limitations when generating images that contain user-specified ch…
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
Sanghun Jung, Jungsoo Lee, Daehoon Gwak +2
Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safety-critical applications. Existing approaches use images of une…
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
Sungha Choi, Sanghun Jung, Huiwon Yun +3
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To addre…