This paper presents ClusterFormer, a universal vision model that is based on the Clustering
paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …

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 …

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 …

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 …

Recently, Transformers have shown promising performance in various vision tasks. To
reduce the quadratic computation complexity caused by each query attending to all …

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 …

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 …