Related papers: Privacy-Preserving Image Classification Using Visi…
Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and…
Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a…
Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced…
The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT…
We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and to ensure that no…
To ensure the privacy of sensitive data used in the training of deep learning models, a number of privacy-preserving methods have been designed by the research community. However, existing schemes are generally designed to work with textual…
Classification of AI-manipulated content is receiving great attention, for distinguishing different types of manipulations. Most of the methods developed so far fail in the open-set scenario, that is when the algorithm used for the…
Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most…
Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…
Visual localization is the task of estimating the camera pose of an image relative to a scene representation. In practice, visual localization systems are often cloud-based. Naturally, this raises privacy concerns in terms of revealing…
Fine-grained classification is a challenging task that involves identifying subtle differences between objects within the same category. This task is particularly challenging in scenarios where data is scarce. Visual transformers (ViT) have…
Vision transformers (ViTs) that model an image as a sequence of partitioned patches have shown notable performance in diverse vision tasks. Because partitioning patches eliminates the image structure, to reflect the order of patches, ViTs…
Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on…
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…
While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance. However, the quadratic…
Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…
The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search engines and other similar tools. In this context, this paper…
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…
Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation. While the vulnerability of CNNs to adversarial attacks is a…
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…