GCD 类似于半监督学习 (SSL),但更具现实性和挑战性,因为 SSL 假定所有未标记的图像都与已标记的图像属于同一类别。不假设未标记数据中的类数是事先已知的会使得 GCD 问题变得更加困难。为了在不知道类号的情况下解决 GCD 问题,我们提出了一个类似于 EM 的框架,在表示学习和类号估计之间交替进行。我们提出了一...
论文地址:[2211.11727] Parametric Classification for Generalized Category Discovery: A Baseline Study (arxiv.org) 代码地址:CVMI-Lab/SimGCD: (ICCV 2023) Parametric Classification for Generalized Category Discovery: A Baseline Study (github.com) 摘要 广义类别发现(GCD)旨在利用从有标签样本中学到的知识,在...
Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery Abstract 在本文中,我们解决了广义类别发现(generalized category discovery, GCD)的问题,即给定一组图像,其中一部分被标记,其余部分未标记,任务是利用来自有标签数据的信息,在无标签数据中自动聚类图像,而无标签数据包含来自标记类的...
Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data by utilizing a few labeled data with only known categories. Due to the lack of supervision and category information, current methods usually perform poorly on...
To address this, this paper explores an aerial image recognition scenario in which a dataset comprises both labeled and unlabeled aerial images, intending to classify all images within the unlabeled subset, termed Generalized Category Discovery (GCD). It is noteworthy that the unlabele...
We address the more unconstrained setting, naming it 'Generalized Category Discovery', and challenge all these assumptions. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. Next, we propose the use of vision ...
Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets, providing a more realistic setting for image recognition. Essentially, GCD needs to remember existing patterns thoroughly to recognize novel categories. Recent state-of-the-art method...
@inproceedings{choi2024contrastive, title={Contrastive Mean-Shift Learning for Generalized Category Discovery}, author={Choi, Sua and Kang, Dahyun and Cho, Minsu}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, year={2024} }...
While strides have been made in the realms of self-supervised and open-world learning towards test-time category discovery, a crucial yet often overlooked question persists: what exactly delineates a category? In this paper, we conceptualize a category through the lens of optimization, viewing it...
Generalized Category Discovery (GCD) utilizes labelled data from seen categories to cluster unlabelled samples from both seen and unseen categories. Previous methods have demonstrated that assigning pseudo-labels for representation learning is effective. However, these methods commonly predict pseudo-labels ...