论文链接:[2305.06144] Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery (arxiv.org) 代码链接:https://github.com/DTennant/GPC这篇文章中忽略了许多细节推导问题,事实…
论文链接:[2304.14310] Incremental Generalized Category Discovery (arxiv.org) 代码链接:DTennant/Incremental-Generalized-Category-Discovery (github.com) 摘要 我们探讨了增量通用类别发现(IGCD)问题。这是一个极具挑战性的增量分类学习问题,其目标是开发出能够正确分类以前所见类别图像的模型,同时发现新的类别。学习...
To address these challenges, we propose a novel computational framework, named AnnoGCD, building on Generalized Category Discovery (GCD) and Anomaly Detection (AD) for automatic cell type annotation. Our semi-supervised method combines labeled and unlabeled data to accurately classify ...
Welcome to the official repository for the Generalized Category Discovery in Semantic Segmentation (GCDSS) project! Overview This repository contains the code implementation for GCDSS. We are currently in the process of organizing and refining the codebase to make it more user-friendly. Currently, ...
Official implementation for AAAI'25 "Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery" - Terminator8758/PAL-GCD
论文链接:[2305.10420] CLIP-GCD: Simple Language Guided Generalized Category Discovery (arxiv.org) 目前未公布代码,idea有点意思,就是文章感觉还不太完整,可以蹲个完整版。 摘要 广义类别发现(GCD)需要一个模型来对未标记数据中的已知类别进行分类并对未知类别进行聚类。先前的方法利用自监督预训练结合对标记数据...
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 Cat…
title={Active generalized category discovery}, author={Ma, Shijie and Zhu, Fei and Zhong, Zhun and Zhang, Xu-Yao and Liu, Cheng-Lin}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={16890--16900}, year={2024} } ``` ## Acknowledgeme...
This project is the offical pytorch implementation for our CVPR2024 paper, Federated Generalized Category Discovery. Code is coming soon. If you find this code useful to your research, please cite the following paper. @article{pu2023federated, title={Federated generalized category discovery}, author...
在本文中,我们研究了广义类别发现(Generalized Category Discovery,简称 GCD)问题,该问题旨在利用已知类别的标记数据知识,对来自已知和未知类别的未标记数据进行聚类。当前的 GCD 方法仅依赖于视觉线索,然而这忽略了人类在发现新视觉类别时多模态感知特性的认知过程。为了解决这一问题,我们提出了一个两阶段的 TextGCD 框...