Related papers: Win-Win: Training High-Resolution Vision Transform…

Reconstructing a 3D object from a 2D image is a well-researched vision problem, with many kinds of deep learning techniques having been tried. Most commonly, 3D convolutional approaches are used, though previous work has shown…

Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural…

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated the remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which…

Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical…

Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in high inference times and memory usage. Additionally, ViT…

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

State-of-the-art deep learning models for computer vision tasks are based on the transformer architecture and often deployed in real-time applications. In this scenario, the resources available for every inference can vary, so it is useful…

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive…

Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing…

We explore the application of Vision Transformer (ViT) for handwritten text recognition. The limited availability of labeled data in this domain poses challenges for achieving high performance solely relying on ViT. Previous…

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

The existing deep learning fusion methods mainly concentrate on the convolutional neural networks, and few attempts are made with transformer. Meanwhile, the convolutional operation is a content-independent interaction between the image and…

Recently, the deep learning technology has been successfully applied in the field of image compression, leading to superior rate-distortion performance. However, a challenge of many learning-based approaches is that they often achieve…

Deep learning methods are notoriously data-hungry, which requires a large number of labeled samples. Unfortunately, the large amount of interactive sample labeling efforts has dramatically hindered the application of deep learning methods,…

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional…

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the…

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a…

Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…