Related papers: Memory Efficient Multi-Scale Line Detector Archite…
We aim to study the multi-scale receptive fields of a single convolutional neural network to detect faces of varied scales. This paper presents our Multi-Scale Receptive Field Face Detector (MSFD), which has superior performance on…
Retinal blood vessel segmentation can extract clinically relevant information from fundus images. As manual tracing is cumbersome, algorithms based on Convolution Neural Networks have been developed. Such studies have used small publicly…
In this paper, we present a novel neural network architecture for retinal vessel segmentation that improves over the state of the art on two benchmark datasets, is the first to run in real time on high resolution images, and its small…
Existing supervised approaches didn't make use of the low-level features which are actually effective to this task. And another deficiency is that they didn't consider the relation between pixels, which means effective features are not…
Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…
Analysis of retinal fundus images is essential for eye-care physicians in the diagnosis, care and treatment of patients. Accurate fundus and/or retinal vessel maps give rise to longitudinal studies able to utilize multimedia image…
Fixed-complexity Sphere Decoder (FSD) is a recently proposed technique for Multiple-Input Multiple-Output (MIMO) detection. It has several outstanding features such as constant throughput and large potential parallelism, which makes it…
Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider…
Computational complexity and storage requirements are crucial factors influencing the performance and efficiency of convolutional neural networks (CNNs) in resource-constrained environments. This paper presents a high-performance embedded…
Real-time Deep Neural Network (DNN) inference with low-latency requirement has become increasingly important for numerous applications in both cloud computing (e.g., Apple's Siri) and edge computing (e.g., Google/Waymo's driverless car).…
We present a novel LSTM cell architecture capable of learning both intra- and inter-perspective relationships available in visual sequences captured from multiple perspectives. Our architecture adopts a novel recurrent joint learning…
Convolutional neural networks (CNNs) require both intensive computation and frequent memory access, which lead to a low processing speed and large power dissipation. Although the characteristics of the different layers in a CNN are…
Transformers excel in Natural Language Processing (NLP) due to their prowess in capturing long-term dependencies but suffer from exponential resource consumption with increasing sequence lengths. To address these challenges, we propose MCSD…
This PhD research introduces three key contributions in the domain of object motion detection: Multi-Hierarchical Spiking Neural Network (MHSNN): A specialized four-layer Spiking Neural Network (SNN) architecture inspired by vertebrate…
Segmentation plays a crucial role in diagnosis. Studying the retinal vasculatures from fundus images help identify early signs of many crucial illnesses such as diabetic retinopathy. Due to the varying shape, size, and patterns of retinal…
We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution…
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…
This paper introduces the Efficient Facial Landmark Detection (EFLD) model, specifically designed for edge devices confronted with the challenges related to power consumption and time latency. EFLD features a lightweight backbone and a…
This paper presents a SYCL implementation of Multi-Layer Perceptrons (MLPs), which targets and is optimized for the Intel Data Center GPU Max 1550. To increase the performance, our implementation minimizes the slow global memory accesses by…
We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of large-scale patches at multiple image-scales during training. Experiments on three fundus image datasets…