Search Results for author: Beiwen Tian

Found 8 papers, 8 papers with code

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

1 code implementation25 Apr 2023 Huan-ang Gao, Beiwen Tian, Pengfei Li, Hao Zhao, Guyue Zhou

While this paradigm is natural for image-level or pixel-level prediction, adapting it to the detection problem is challenged by the issue of proposal matching.

3D Object Detection object-detection +1

Delving into Shape-aware Zero-shot Semantic Segmentation

1 code implementation CVPR 2023 Xinyu Liu, Beiwen Tian, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Hao Zhao, Guyue Zhou

Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.

Image Segmentation Semantic Segmentation

VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling

1 code implementation20 Oct 2022 Beiwen Tian, Liyi Luo, Hao Zhao, Guyue Zhou

In the first stage, we perform self-supervised representation learning on unlabeled points with the proposed Viewpoint Bottleneck loss function.

Representation Learning Scene Parsing

TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation

1 code implementation19 Oct 2022 Pengfei Li, Beiwen Tian, Yongliang Shi, Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang

As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on.

Instance Segmentation Referring Expression +2

Language-guided Semantic Style Transfer of 3D Indoor Scenes

1 code implementation16 Aug 2022 Bu Jin, Beiwen Tian, Hao Zhao, Guyue Zhou

We address the new problem of language-guided semantic style transfer of 3D indoor scenes.

Style Transfer

Unsupervised Cross-Task Generalization via Retrieval Augmentation

1 code implementation17 Apr 2022 Bill Yuchen Lin, Kangmin Tan, Chris Miller, Beiwen Tian, Xiang Ren

Humans can perform unseen tasks by recalling relevant skills acquired previously and then generalizing them to the target tasks, even if there is no supervision at all.


Cannot find the paper you are looking for? You can Submit a new open access paper.