Abstract Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales …
J Yang, D Parikh, D Batra - … of the IEEE conference on computer …, 2016 - cv-foundation.org
In this paper, we propose a recurrent framework for joint unsupervised learning of deep representations and image clusters. In our framework, successive operations in a clustering …
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 …
Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general …
K Song, S Zhang, Z Luo, T Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented" views" of the same image closer while pushing …
Z Wang, Y Wang, Z Wu, J Lu… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature …
With the remarkable progress of deep neural networks in computer vision, data mixing augmentation techniques are widely studied to alleviate problems of degraded …
Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic …