5 papers
MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds
Inseok Kong, Geunyoung Jung, Jiyoung Jung
3D point cloud models suffer significant performance degradation under distribution shifts caused by sensor noise, occlusions, and environmental changes. Test-time adaptation (TTA)…
APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
Geunyoung Jung, Soohong Kim, Inseok Kong +1
The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Although various defense methods…
P3T: Prototypical Point-level Prompt Tuning with Enhanced Generalization for 3D Vision-Language Models
Geunyoung Jung, Soohong Kim, Kyungwoo Song +1
With the rise of pre-trained models in the 3D point cloud domain for a wide range of real-world applications, adapting them to downstream tasks has become increasingly important. H…
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
Changdae Oh, Gyeongdeok Seo, Geunyoung Jung +4
With a surge of large-scale pre-trained models, parameter-efficient transfer learning (PETL) of large models has garnered significant attention. While promising, they commonly rely…
Enhancing Visual Classification using Comparative Descriptors
Hankyeol Lee, Gawon Seo, Wonseok Choi +3
The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs)…