一年级博士生安文斌论文被AAAI2023录用 - 首页
Paper ID: 4397
Paper Title: Generalized Category Discovery with Decoupled Prototypical Network
Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories. Without considering differences between known and novel categories, current methods learn about them in a coupled manner, which can hurt model's generalization and discriminative ability. Furthermore, the coupled training manner prevents these models transferring category-specific knowledge from labeled data to unlabeled data, which can lose high-level semantic information and further impair model performance. To mitigate above limitations, we present a novel Decoupled Prototypical Network (DPN). By formulating a bipartite matching problem for category prototypes, DPN can not only decouple known and novel categories to achieve different training targets for them effectively, but also align known categories in labeled and unlabeled data to transfer category-specific knowledge and learn high-level semantics. Furthermore, DPN can learn more discriminative features for both known and novel categories through our proposed Semantic-aware Prototypical Learning (SPL). Besides capturing meaningful semantic information to learn about known and novel categories, SPL can also alleviate the noise of hard pseudo labels through semantic-weighted soft assignment. Extensive experiments show that DPN outperforms state-of-the-art models by a large margin on all evaluation metrics across multiple benchmark datasets.
Authors: Wenbing An, Feng Tian, Qinghua Zheng, Wei Ding, Qianying Wang, Ping Chen.