中文
相关论文

相关论文: A Hidden Stumbling Block in Generalized Category D…

200 篇论文

Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artificial datasets with balanced distributions. However,…

人工智能 · 计算机科学 2025-07-31 Cuong Manh Hoang

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…

计算与语言 · 计算机科学 2023-03-16 Wenbin An , Feng Tian , Qinghua Zheng , Wei Ding , QianYing Wang , Ping Chen

In this paper, we study the problem of Generalized Category Discovery (GCD), which aims to cluster unlabeled data from both known and unknown categories using the knowledge of labeled data from known categories. Current GCD methods rely on…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Haiyang Zheng , Nan Pu , Wenjing Li , Nicu Sebe , Zhun Zhong

Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonly leverage transferable representations from pre-trained…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Bo Ye , Kai Gan , Tong Wei , Min-Ling Zhang

Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Jizhou Han , Chenhao Ding , Yuhang He , Qiang Wang , Shaokun Wang , SongLin Dong , Yihong Gong

Constantly discovering novel concepts is crucial in evolving environments. This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD), which aims to incrementally discover new classes from unlabeled data…

计算机视觉与模式识别 · 计算机科学 2024-10-11 Shijie Ma , Fei Zhu , Zhun Zhong , Wenzhuo Liu , Xu-Yao Zhang , Cheng-Lin Liu

Generalized Category Discovery (GCD) aims to recognize unlabeled images from known and novel classes by distinguishing novel classes from known ones, while also transferring knowledge from another set of labeled images with known classes.…

计算机视觉与模式识别 · 计算机科学 2025-07-10 Qiyuan Dai , Hanzhuo Huang , Yu Wu , Sibei Yang

In this paper, we address the problem of generalized category discovery (GCD), \ie, given a set of images where part of them are labelled and the rest are not, the task is to automatically cluster the images in the unlabelled data,…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Bingchen Zhao , Xin Wen , Kai Han

Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples. Previous methods generally employ…

计算机视觉与模式识别 · 计算机科学 2024-02-02 Yuanpeng Tu , Zhun Zhong , Yuxi Li , Hengshuang Zhao

Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Bhupendra Solanki , Ashwin Nair , Mainak Singha , Souradeep Mukhopadhyay , Ankit Jha , Biplab Banerjee

We tackle the issue of generalized category discovery (GCD). GCD considers the open-world problem of automatically clustering a partially labelled dataset, in which the unlabelled data may contain instances from both novel categories and…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Shaozhe Hao , Kai Han , Kwan-Yee K. Wong

Accurately credit default prediction faces challenges due to imbalanced data and low correlation between features and labels. Existing default prediction studies on the basis of gradient boosting decision trees (GBDT), deep learning…

计算工程、金融与科学 · 计算机科学 2023-12-06 Yandan Tan , Hongbin Zhu , JieWu , Hongfeng Chai

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph…

计算机视觉与模式识别 · 计算机科学 2021-08-13 Zhihao Peng , Hui Liu , Yuheng Jia , Junhui Hou

Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes. Training a parametric classifier solely on image features often leads to overfitting to old…

计算机视觉与模式识别 · 计算机科学 2026-02-20 Lorenzo Caselli , Marco Mistretta , Simone Magistri , Andrew D. Bagdanov

Generalized Category Discovery (GCD) is an open-world problem that clusters unlabeled data by leveraging knowledge from partially labeled categories. A key challenge is that unlabeled data may contain both known and novel categories.…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Haiyang Zheng , Nan Pu , Wenjing Li , Nicu Sebe , Zhun Zhong

In open-world scenarios, Generalized Category Discovery (GCD) requires identifying both known and novel categories within unlabeled data. However, existing methods often suffer from prototype confusion caused by shortcut learning, which…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Kailin Lyu , Jianwei He , Long Xiao , Jianing Zeng , Liang Fan , Lin Shu , Jie Hao

Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training…

计算机视觉与模式识别 · 计算机科学 2020-10-30 Xiaojiang Peng , Kai Wang , Zhaoyang Zeng , Qing Li , Jianfei Yang , Yu Qiao

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the…

机器学习 · 计算机科学 2025-02-25 Behrooz Azarkhalili , Maxwell Libbrecht

Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge…

计算与语言 · 计算机科学 2023-12-29 Wenbin An , Feng Tian , Wenkai Shi , Yan Chen , Yaqiang Wu , Qianying Wang , Ping Chen

Recent advancements have shown promise in applying traditional Semi-Supervised Learning strategies to the task of Generalized Category Discovery (GCD). Typically, this involves a teacher-student framework in which the teacher imparts…

计算机视觉与模式识别 · 计算机科学 2024-10-28 Haonan Lin , Wenbin An , Jiahao Wang , Yan Chen , Feng Tian , Mengmeng Wang , Guang Dai , Qianying Wang , Jingdong Wang