Related papers: Time Series Representations for Classification Lie…
The Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. However, ViTs are ill-suited for private inference using secure multi-party computation (MPC)…
The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the…
Remote sensing scene classification has been extensively studied for its critical roles in geological survey, oil exploration, traffic management, earthquake prediction, wildfire monitoring, and intelligence monitoring. In the past, the…
Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. Traditionally, convolutional neural networks (CNNs) dominated this domain,…
The remarkable representational power of Vision Transformers (ViTs) remains underutilized in few-shot image classification. In this work, we introduce ViT-ProtoNet, which integrates a ViT-Small backbone into the Prototypical Network…
Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of…
Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the…
Recently, Vision Transformers (ViTs) have achieved unprecedented effectiveness in the general domain of image classification. Nonetheless, these models remain underexplored in the field of deepfake detection, given their lower performance…
As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved…
Deep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i.e., predicting one result per video. However, challenges arise when adapting existing deep video models to dense…
High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most…
Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete,…
As deep learning models increasingly find applications in critical domains such as medical imaging, the need for transparent and trustworthy decision-making becomes paramount. Many explainability methods provide insights into how these…
We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…
Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…
Vision Transformer (ViT)-based models have shown state-of-the-art performance (e.g., accuracy) in vision-based AI tasks. However, realizing their capability in resource-constrained embedded AI systems is challenging due to their inherent…
The Vision Transformer architecture has shown to be competitive in the computer vision (CV) space where it has dethroned convolution-based networks in several benchmarks. Nevertheless, convolutional neural networks (CNN) remain the…
Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from…
Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale…
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…