相关论文: MaxViT: Multi-Axis Vision Transformer

Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we present Mobile…

Model binarization can significantly compress model size, reduce energy consumption, and accelerate inference through efficient bit-wise operations. Although binarizing convolutional neural networks have been extensively studied, there is…

Change detection in remote sensing images is essential for tracking environmental changes on the Earth's surface. Despite the success of vision transformers (ViTs) as backbones in numerous computer vision applications, they remain…

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks. Building upon this paradigm, Vision…

Secure multi-party computation (MPC) enables computation directly on encrypted data and protects both data and model privacy in deep learning inference. However, existing neural network architectures, including Vision Transformers (ViTs),…

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

Glaucoma is a prevalent eye disease that progresses silently without symptoms. If not detected and treated early, it can cause permanent vision loss. Computer-assisted diagnosis systems play a crucial role in timely and efficient…

Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis. While Transformers have…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Mobile vision transformers (MobileViT) can achieve state-of-the-art performance across several mobile vision tasks, including classification and detection. Though these models have fewer parameters, they have high latency as compared to…

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performance, which is burdensome to deploy on resource-constrained…

Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, $\pi^3$ and MapAnything have demonstrated remarkable performance with relatively…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost makes deploying state-of-the-art high-resolution dense…

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…