AutoNovel(又名 Rankstats)[17、18] 使用三阶段方法解决 NCD 问题。该模型首先对所有数据进行自我监督训练,以进行低级表示学习。然后,在标记数据的全面监督下进一步训练以捕获更高级别的语义信息。最后,进行联合学习阶段,将知识从带标签的数据转移到带排名统计的未带标签的数据。Zhao 和 Han [51] 提出了一个具有两...
novel category discovery (NCD) 通过转移从已知类的标记实例中学习到的知识来自动发现新类,假设无标签数据仅包含来自新类的实例。 Generalized category discovery (GCD) 进一步放宽了NCD中的假设,并处理了一个更广义的设置,其中未标记的数据包含已知和新类别的实例。现有方法假设类数是已知的先验或预先计算好的。 在...
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。学习是在一系列时间步骤中进行的,模型在每次迭代时都会获得新的标记和未标记数据,并...
While some methods utilizing offline continual learning have been proposed for novel category discovery, they neglect the continuity of data streams in real-world settings. In this work, we introduce Online Continuous Generalized Category Discovery ( OCGCD ), which considers the dynamic nature of ...
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...
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...
One major conundrum with both Generalized Category Discovery and Novel Category Discovery is that the definition of the category has remained undetermined. This complication can be overlooked when the granularity of categories at test time is similar to training time. However, for more realistic applica...
(2021). Joint representation learning and novel category discovery on single-and multi-modal data. In ICCV. Jiang, D., Sun, S., & Yu, Y. (2021a). Revisiting flow generative models for out-of-distribution detection. In International conference on learning representations. Jiang, K., Xie, ...
@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} }...