1 code implementation • 27 Dec 2023 • Wenbin An, Feng Tian, Wenkai Shi, Yan Chen, Yaqiang Wu, Qianying Wang, Ping Chen
On the other hand, we use these prototypes to calibrate noisy prototypes estimated from unlabeled data based on category similarities, which allows for more accurate estimation of prototypes for novel categories that can be used as reliable learning targets later.
no code implementations • 18 Dec 2023 • Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, Qianying Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen
Then we propose a Scalable Query strategy to allow LLMs to choose true neighbors of the selected samples from multiple candidate samples.
1 code implementation • 24 Oct 2023 • Wenkai Shi, Wenbin An, Feng Tian, Qinghua Zheng, Qianying Wang, Ping Chen
New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents.
1 code implementation • 16 Oct 2023 • Wenbin An, Feng Tian, Wenkai Shi, Yan Chen, Qinghua Zheng, Qianying Wang, Ping Chen
Specifically, we retrieve k-nearest neighbors of a query as its positive keys to capture semantic similarities between data and then aggregate information from the neighbors to learn compact cluster representations, which can make fine-grained categories more separatable.
1 code implementation • 31 May 2023 • Guofan Fan, Zekun Qi, Wenkai Shi, Kaisheng Ma
Geometry and color information provided by the point clouds are both crucial for 3D scene understanding.
Ranked #1 on Unsupervised 3D Semantic Segmentation on ScanNetV2