Related papers: EfficientViT: Multi-Scale Linear Attention for Hig…

The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Federated learning research has recently shifted from Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs) due to their superior capacity. ViTs training demands higher computational resources due to the lack of 2D inductive…

Recent advances in video diffusion models have shifted towards transformer-based architectures, achieving state-of-the-art video generation but at the cost of quadratic attention complexity, which severely limits scalability for longer…

Facial Beauty Prediction (FBP) has made significant strides with the application of deep learning, yet state-of-the-art models often exhibit critical limitations, including architectural constraints, inherent demographic biases, and a lack…

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices…

In recent years, raw video denoising has garnered increased attention due to the consistency with the imaging process and well-studied noise modeling in the raw domain. However, two problems still hinder the denoising performance. Firstly,…

Since the breakthrough performance of AlexNet in 2012, convolutional neural networks (convnets) have grown into extremely powerful vision models. Deep learning researchers have used convnets to perform vision tasks with accuracy that was…

While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…

Vision transformers have become one of the most important models for computer vision tasks. Although they outperform prior works, they require heavy computational resources on a scale that is quadratic to the number of tokens, $N$. This is…

Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing…

We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting,…

Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big…

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

In this study, we present a pragmatic lightweight pose estimation model. Our model can achieve real-time predictions using low-power embedded devices. This system was found to be very accurate and achieved a 94.5% accuracy of SOTA HRNet…

Visual intelligence at the edge is becoming a growing necessity for low latency applications and situations where real-time decision is vital. Object detection, the first step in visual data analytics, has enjoyed significant improvements…

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with…

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…

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

Vision Transformers (ViTs) have recently garnered considerable attention, emerging as a promising alternative to convolutional neural networks (CNNs) in several vision-related applications. However, their large model sizes and high…