这篇paper的核心idea主要就是dino-based的vit model + supervised contrastive learning 产生聚类性比较强的representations,然后使用 semi-kmeans 来进行聚类,具体可见代码,比较简单,这里就不啰嗦了。 https://github.com/sgvaze/generalized-category-discoverygithub.com/sgvaze/generalized-category-discovery 不过作为...
To this end, we propose Mutual-Support Generalized Category Discovery (MSGCD), a framework that unifies these two paradigms, leveraging their strengths in a mutually reinforcing manner. It simultaneously learns high-quality pseudo-labels and discriminative representations. It incorporates a novelMutual-...
(2021b). Joint representation learning and novel category discovery on single-and multi-modal data. In IEEE/CVF International conference on computer vision (ICCV), (pp. 610–619) Joseph, K., Paul, S., Aggarwal, G., Biswas, S., Rai, P., Han, K., & Balasubramanian, V. N. (2022a...
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...
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...
@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}} ...
(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, ...
Discovering Novel Mechanisms for Alzheimer's Disease by Machine Learning 3249 43:00 Understanding & Generating Natural(Biological & Human)Language & Beyond 3152 34:00 浅谈纳米生物医学与人工智能结合在癌症精准检测中的应用 3440 01:15:00 视频理解中的时空特征学习 2952 42:00 “视觉与语言”跨模态智能及...
and then emphasized the importance of features using self-attention51. Denoising the signal and then classifying it is a novel innovation. Due to the two-stage nature of the H-CSG method22, where the denoising and detection stages are trained separately, the results are affected by the denoisi...
In particular, the contrastive-learning branch provides reliable distribution estimation to regularize the predictions of the pseudo-labeling branch, which in turn guides contrastive learning through self-balanced knowledge transfer and a proposed novel contrastive loss. We compare BaCon with state-of-the...