.png){kind=icon}
返回
Efficient Representation Learning for Generalized Category Discovery
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112214.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Generalized Category Discovery (GCD) aims to discover and cluster data from previously unseen classes. Numerous studies have delved into GCD; however, they either overlooked the significance of representation learning or naively adapt the contrastive loss from self-supervised learning without further refinements. Therefore, in this paper, we propose a simple yet effective method to address this task. Our first contribution is to design a robust Divide-and-Combine strategy with an improved contrastive loss to generate informative features. Subsequently, in light of the scarce supervised signals, we propose a Neighborhood-based Sampling module based on the analysis of cluster-level alignment and uniformity to better discover novel categories. Ultimately, to boost the model's ability to learn from unlabeled data, we adopt a fusion training approach utilizing combinational patch features and the deterministic threshold to selectively identify high-confidence samples. We unify these learning processes within a single framework and jointly optimize. Extensive experiments across three general datasets and four fine-grained benchmark datasets show the compelling evidence for the superiority of our proposed method- E fficient R epresentation L earning for G eneralized C ategory D iscovery (ERL4GCD).
Keyword:
Generalized category discovery
Open-world problem
Image classification
Representation learning
期刊
K
IF:
7.6
论文数:
1.2W
被引数:
4.5W
机构
引用论文
miRNA-Based Potential Biomarkers and New Molecular Insights in Ulcerative Colitis溃疡性结肠炎中基于miRNA的潜在生物标志物和新分子见解
OAAI
.png){kind=icon}
OAAI分享收藏Graduated compression stockings: Physiological and perceptual responses during and after exercise
PREAI
分享收藏
查看更多内容