no code implementations • 28 Mar 2024 • Haonan Lin, Mengmeng Wang, Yan Chen, Wenbin An, Yuzhe Yao, Guang Dai, Qianying Wang, Yong liu, Jingdong Wang
While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centered images, novel challenges arise with a nuanced task of "identity fine editing": precisely modifying specific features of a subject while maintaining its inherent identity and context.
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.
2 code implementations • 28 Nov 2022 • Wenbin An, Feng Tian, Qinghua Zheng, Wei Ding, Qianying Wang, Ping Chen
Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance.
1 code implementation • 14 Oct 2022 • Wenbin An, Feng Tian, Ping Chen, Siliang Tang, Qinghua Zheng, Qianying Wang
Novel category discovery aims at adapting models trained on known categories to novel categories.