Related papers: Efficient Scale-Permuted Backbone with Learned Res…

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…

Spine segmentation, based on ultrasound volume projection imaging (VPI), plays a vital role for intelligent scoliosis diagnosis in clinical applications. However, this task faces several significant challenges. Firstly, the global…

An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation. In…

Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems. Due to high in-memory overheads, traditional index structures become difficult to process the…

Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional…

Unsupervised dimensionality reduction is one of the commonly used techniques in the field of high dimensional data recognition problems. The deep autoencoder network which constrains the weights to be non-negative, can learn a low…

Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…

Vision Transformers have shown great potential in computer vision tasks. Most recent works have focused on elaborating the spatial token mixer for performance gains. However, we observe that a well-designed general architecture can…

Accurate waste classification is vital for achieving sustainable waste management and reducing the environmental footprint of urbanization. Misclassification of recyclable materials contributes to landfill accumulation, inefficient…

Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and…

Recent research efforts in optical computing have gravitated towards developing optical neural networks that aim to benefit from the processing speed and parallelism of optics/photonics in machine learning applications. Among these…

Scaling CNN training is necessary to keep up with growing datasets and reduce training time. We also see an emerging need to handle datasets with very large samples, where memory requirements for training are large. Existing training…

With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various…

Robust object skeleton detection requires to explore rich representative visual features and effective feature fusion strategies. In this paper, we first re-visit the implementation of HED, the essential principle of which can be ideally…

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

In this work, we tackle model efficiency by exploiting redundancy in the \textit{implicit structure} of the building blocks of convolutional neural networks. We start our analysis by introducing a general definition of Composite Kernel…

Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks. However, the computational complexity increases dramatically as well…

In this paper we introduce a new neural network architecture designed to use in embedded vision applications. It merges the best working practices of network architectures like MobileNets and ResNets to our named RMNet architecture. We also…

This study introduces an AI-driven skin lesion classification algorithm built on an enhanced Transformer architecture, addressing the challenges of accuracy and robustness in medical image analysis. By integrating a multi-scale feature…