Scene graph is a structured representation of a scene that can clearly express the objects,
attributes, and relationships between objects in the scene. As computer vision technology …

Deep learning techniques have led to remarkable breakthroughs in the field of object
detection and have spawned a lot of scene-understanding tasks in recent years. Scene …

We identify empirical scaling laws for the cross-entropy loss in four domains: generative
image modeling, video modeling, multimodal image $\leftrightarrow $ text models, and …

Large-scale labeled data are generally required to train deep neural networks in order to
obtain better performance in visual feature learning from images or videos for computer …

Following the success in advancing natural language processing and understanding,
transformers are expected to bring revolutionary changes to computer vision. This work …

Clustering is a class of unsupervised learning methods that has been extensively applied
and studied in computer vision. Little work has been done to adapt it to the end-to-end …

This paper presents a study of semi-supervised learning with large convolutional networks.
We propose a pipeline, based on a teacher/student paradigm, that leverages a large …

Image classification systems recently made a giant leap with the advancement of deep
neural networks. However, these systems require an excessive amount of labeled data to be …

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant
performance in image classification. Many large-scale datasets are collected from websites …

The success of deep learning in vision can be attributed to:(a) models with high capacity;(b)
increased computational power; and (c) availability of large-scale labeled data. Since 2012 …