Search Results - "Yang, Jihan"

Tuning C–C sp2/sp3 ratio of DLC films in FCVA system for biomedical application by Rao, Xi, Yang, Jihan, Chen, Zilin, Yuan, Yidie, Chen, Qiubing, Feng, Xue, Qin, Lizhao, Zhang, Yongping

“…Diamond like carbon (DLC) films with different C–C sp2/sp3 ratios were prepared by tuning the N2 flow rate in a filtered cathodic vacuum arc (FCVA) system. The…”
Get full text

Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability by He, Ruifei, Sun, Shuyang, Yang, Jihan, Bai, Song, Qi, Xiaojuan

“…Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model…”
Get full text

Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation by Xu, Ruijia, Li, Guanbin, Yang, Jihan, Lin, Liang

“…Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not…”
Get full text

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection by Yang, Jihan, Shi, Shaoshuai, Wang, Zhe, Li, Hongsheng, Qi, Xiaojuan

“…We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we…”
Get full text

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation by He, Ruifei, Yang, Jihan, Qi, Xiaojuan

“…While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic…”
Get full text

ST3D++: Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection by Yang, Jihan, Shi, Shaoshuai, Wang, Zhe, Li, Hongsheng, Qi, Xiaojuan

“…In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object…”
Get full text

Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding by Ding, Runyu, Yang, Jihan, Xue, Chuhui, Zhang, Wenqing, Bai, Song, Qi, Xiaojuan

“…Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is…”
Get full text

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding by Ding, Runyu, Yang, Jihan, Xue, Chuhui, Zhang, Wenqing, Bai, Song, Qi, Xiaojuan

“…Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. The recent breakthrough of 2D…”
Get full text

Replication and bioactivation of Ti-based alloy scaffold macroscopically identical to cancellous bone from polymeric template with TiNbZr powders by Rao, Xi, Yang, Jihan, Li, Jing, Feng, Xue, Chen, Zilin, Yuan, Yidie, Yong, Binglian, Chu, Chenglin, Tan, Xiaodong, Song, Qunliang

“…In the present work, a new type of porous Ti-based alloy scaffold with high porosity (about 75%) and interconnected pores in the range of 300-1000 µm was…”
Get full text

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding by Yang, Jihan, Ding, Runyu, Deng, Weipeng, Wang, Zhe, Xiaojuan, Q.

“…We propose a lightweight and scalable Regional Point-Language Contrastive learning framework, namely RegionPLC, for open-world 3D scene understanding, aiming…”
Get full text

V-IRL: Grounding Virtual Intelligence in Real Life by Yang, Jihan, Ding, Runyu, Brown, Ellis, Qi, Xiaojuan, Xie, Saining

“…There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created. To develop AI agents that can…”
Get full text

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding by Yang, Jihan, Ding, Runyu, Deng, Weipeng, Wang, Zhe, Qi, Xiaojuan

“…We propose a lightweight and scalable Regional Point-Language Contrastive learning framework, namely \textbf{RegionPLC}, for open-world 3D scene understanding,…”
Get full text

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation by He, Ruifei, Yang, Jihan, Qi, Xiaojuan

“…While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic…”
Get full text

Can 3D Vision-Language Models Truly Understand Natural Language? by Deng, Weipeng, Yang, Jihan, Ding, Runyu, Liu, Jiahui, Li, Yijiang, Qi, Xiaojuan, Ngai, Edith

“…Rapid advancements in 3D vision-language (3D-VL) tasks have opened up new avenues for human interaction with embodied agents or robots using natural language…”
Get full text

Towards Efficient 3D Object Detection with Knowledge Distillation by Yang, Jihan, Shi, Shaoshuai, Ding, Runyu, Wang, Zhe, Qi, Xiaojuan

“…Despite substantial progress in 3D object detection, advanced 3D detectors often suffer from heavy computation overheads. To this end, we explore the potential…”
Get full text

DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation by Ding, Runyu, Yang, Jihan, Jiang, Li, Qi, Xiaojuan

“…Deep learning approaches achieve prominent success in 3D semantic segmentation. However, collecting densely annotated real-world 3D datasets is extremely…”
Get full text

Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability by He, Ruifei, Sun, Shuyang, Yang, Jihan, Bai, Song, Qi, Xiaojuan

“…Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model…”
Get full text

Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding by Ding, Runyu, Yang, Jihan, Xue, Chuhui, Zhang, Wenqing, Bai, Song, Qi, Xiaojuan

“…Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is…”
Get full text

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection by Yang, Jihan, Shi, Shaoshuai, Wang, Zhe, Li, Hongsheng, Qi, Xiaojuan

“…In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object…”
Get full text

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding by Ding, Runyu, Yang, Jihan, Xue, Chuhui, Zhang, Wenqing, Bai, Song, Qi, Xiaojuan

“…Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. The recent breakthrough of 2D…”
Get full text