Related papers: A lightweight Transformer-based model for fish lan…

This paper introduces FaceLiVT, a lightweight yet powerful face recognition model that integrates a hybrid Convolution Neural Network (CNN)-Transformer architecture with an innovative and lightweight Multi-Head Linear Attention (MHLA)…

Vision transformers (ViT) have been shown to allow for more flexible feature detection and can outperform convolutional neural network (CNN) when pre-trained on sufficient data. Due to their promising feature detection capabilities, we…

In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…

Hybrids of Convolutional Neural Network (CNN) and Vision Transformer (ViT) have outperformed pure CNN or ViT architecture. However, since these architectures require large parameters and incur large computational costs, they are unsuitable…

In many medical imaging tasks, convolutional neural networks (CNNs) efficiently extract local features hierarchically. More recently, vision transformers (ViTs) have gained popularity, using self-attention mechanisms to capture global…

The transformer model has gained widespread adoption in computer vision tasks in recent times. However, due to the quadratic time and memory complexity of self-attention, which is proportional to the number of input tokens, most existing…

The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e.g., image-level, region-level, and pixel-level are diverging. Generally, network structures designed specifically…

Side-scan sonar (SSS) imagery presents unique challenges in the classification of man-made objects on the seafloor due to the complex and varied underwater environments. Historically, experts have manually interpreted SSS images, relying on…

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly…

Remote sensing datasets offer significant promise for tackling key classification tasks such as land-use categorization, object presence detection, and rural/urban classification. However, many existing studies tend to focus on narrow tasks…

Transformers are state-of-the-art deep learning models that are composed of stacked attention and point-wise, fully connected layers designed for handling sequential data. Transformers are not only ubiquitous throughout Natural Language…

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We…

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the…

Convolutional Neural Networks (CNNs) for computer vision sometimes struggle with understanding images in a global context, as they mainly focus on local patterns. On the other hand, Vision Transformers (ViTs), inspired by models originally…

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…

Transformers are popular neural network models that use layers of self-attention and fully-connected nodes with embedded tokens. Vision Transformers (ViT) adapt transformers for image recognition tasks. In order to do this, the images are…

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes. While Convolutional Neural Networks (CNNs) have…

Place recognition is a fundamental task for robotic application, allowing robots to perform loop closure detection within simultaneous localization and mapping (SLAM), and achieve relocalization on prior maps. Current range image-based…

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…

Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in…