Related papers: Slimmable ConvNeXt: Width-Adaptive Inference for E…

Gesture recognition using low-resolution instantaneous HD-sEMG images opens up new avenues for the development of more fluid and natural muscle-computer interfaces. However, the data variability between inter-session and inter-subject…

Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior…

Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores…

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational…

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…

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

Intelligent edge devices with built-in processors vary widely in terms of capability and physical form to perform advanced Computer Vision (CV) tasks such as image classification and object detection, for example. With constant advances in…

This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e.g., image classification, for efficiency as well as accuracy in transfer learning. We call the concept…

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is necessary for fast inference. We show that trivially evaluating…

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…

Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor…

As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited…

Convolutional neural networks (CNNs) and vision transformers (ViTs) have become essential in computer vision for local and global feature extraction. However, aggregating these architectures in existing methods often results in…

Medical image segmentation plays a vital role in various clinical applications, enabling accurate delineation and analysis of anatomical structures or pathological regions. Traditional CNNs have achieved remarkable success in this field.…

Slimmable Neural Networks (S-Net) is a novel network which enabled to select one of the predefined proportions of channels (sub-network) dynamically depending on the current computational resource availability. The accuracy of each…

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt,…

We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime. Our method trains a cohort of…

Most feedforward convolutional neural networks spend roughly the same efforts for each pixel. Yet human visual recognition is an interaction between eye movements and spatial attention, which we will have several glimpses of an object in…

The main contributions of our work are two-fold. First, we present a Self-Attention MobileNet, called SA-MobileNet Network that can model long-range dependencies between the image features instead of processing the local region as done by…