Related papers: ViG: Linear-complexity Visual Sequence Learning wi…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are two dominant models for image analysis. While CNNs excel at extracting multi-scale features and ViTs effectively capture global dependencies, both suffer from high…

Recent studies have demonstrated the effectiveness of Gated Linear Units (GLU) in enhancing transformer models, particularly in Large Language Models (LLMs). Additionally, utilizing a parallel configuration within each Transformer block…

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects. Though Vision GNN (ViG) adopts graph-level features…

The Vision Transformer (ViT) has made significant advancements in computer vision, utilizing self-attention mechanisms to achieve state-of-the-art performance across various tasks, including image classification, object detection, and…

Vision Transformers (ViTs) have shown promise in medical image semantic segmentation (MISS) by capturing long-range correlations. However, ViTs often struggle to model local spatial information effectively, which is essential for accurately…

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Document pre-trained models and grid-based models have proven to be very effective on various tasks in Document AI. However, for the document layout analysis (DLA) task, existing document pre-trained models, even those pre-trained in a…

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce…

Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer…

Inspired by human visual attention, deep neural networks have widely adopted attention mechanisms to learn locally discriminative attributes for challenging visual classification tasks. However, existing approaches primarily emphasize the…

Vision transformers (ViTs) are emerging with significantly improved accuracy in computer vision tasks. However, their complex architecture and enormous computation/storage demand impose urgent needs for new hardware accelerator design…

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features…

Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To…

Recently, there has been a surge of significant interest on application of Deep Learning (DL) models to autonomously perform hand gesture recognition using surface Electromyogram (sEMG) signals. DL models are, however, mainly designed to be…

In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed. Specifically, the frame sampling policy uses weighted…

Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) face inherent challenges in image matting, particularly in preserving fine structural details. ViTs, with their global receptive field enabled by the self-attention…

Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational…

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…