Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discovery
2024-10-17
会议录名称ARXIV
发表状态待投递
DOIarXiv:2410.13285
摘要

We tackle the generalized category discovery (GCD) problem, which aims to discover novel classes in unlabeled datasets by leveraging the knowledge of known classes. Previous works utilize the known class knowledge through shared representation spaces. Despite their progress, our analysis experiments show that novel classes can achieve impressive clustering results on the feature space of a known class pre-trained model, suggesting that existing methods may not fully utilize known class knowledge. To address it, we introduce a novel concept learning framework for GCD, named ConceptGCD, that categorizes concepts into two types: derivable and underivable from known class concepts, and adopts a stage-wise learning strategy to learn them separately. Specifically, our framework first extracts known class concepts by a known class pre-trained model and then produces derivable concepts from them by a generator layer with a covariance-augmented loss. Subsequently, we expand the generator layer to learn underivable concepts in a balanced manner ensured by a concept score normalization strategy and integrate a contrastive loss to preserve previously learned concepts. Extensive experiments on various benchmark datasets demonstrate the superiority of our approach over the previous state-of-the-art methods. Code will be available soon.

URL查看原文
WOS类目Computer Science, Software Engineering
WOS记录号PPRN:115354078
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/446055
专题信息科学与技术学院_博士生
信息科学与技术学院_PI研究组_何旭明组
信息科学与技术学院_硕士生
共同第一作者Gu, Peiyan
通讯作者He, Xuming
作者单位
1.ShanghaiTech Univ, Shanghai, Peoples R China
2.Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China
第一作者单位上海科技大学
通讯作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Zhang, Chuyu,Gu, Peiyan,Yu, Xueyang,et al. Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discovery[C],2024.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zhang, Chuyu]的文章
[Gu, Peiyan]的文章
[Yu, Xueyang]的文章
百度学术
百度学术中相似的文章
[Zhang, Chuyu]的文章
[Gu, Peiyan]的文章
[Yu, Xueyang]的文章
必应学术
必应学术中相似的文章
[Zhang, Chuyu]的文章
[Gu, Peiyan]的文章
[Yu, Xueyang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。