We present a general methodology that learns to classify images without labels by leveraging pretrained feature extractors. Our approach involves self-distillation training of …
We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (ie non-pyramidal) transformer model designed for general visual recognition with high …
H Liu, M Shao, S Li, Y Fu - Proceedings of the 22nd ACM SIGKDD …, 2016 - dl.acm.org
Image clustering has been a critical preprocessing step for vision tasks, eg, visual concept discovery, content-based image retrieval. Conventional image clustering methods use …
Traditional image clustering methods take a two-step approach, feature learning and clustering, sequentially. However, recent research results demonstrated that combining the …
K Do, T Tran, S Venkatesh - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method consists of two heads that share the same backbone …
For many image clustering problems, replacing raw image data with features extracted by a pretrained convolutional neural network (CNN), leads to better clustering performance …
K Liu, T Wu, C Liu, G Guo - arXiv preprint arXiv:2203.03937, 2022 - arxiv.org
Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all …
X Deng, D Huang, DH Chen, CD Wang, JH Lai - Pattern Recognition, 2023 - Elsevier
Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and clustering via deep neural networks. In its latest developments …
G Chen, X Li, Y Yang, W Wang - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
We investigate a fundamental aspect of machine vision: the measurement of features by revisiting clustering one of the most classic approaches in machine learning and data …