Related papers: Algorithm-hardware Co-design for Deformable Convol…
Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with…
Convolutional neural network (CNN) accelerators implemented on Field-Programmable Gate Arrays (FPGAs) are typically designed with a primary focus on maximizing performance, often measured in giga-operations per second (GOPS). However,…
Vision Transformers (ViTs) have achieved significant success in computer vision. However, their intensive computations and massive memory footprint challenge ViTs' deployment on embedded devices, calling for efficient ViTs. Among them,…
Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…
Recently, the field of deep learning has received great attention by the scientific community and it is used to provide improved solutions to many computer vision problems. Convolutional neural networks (CNNs) have been successfully used to…
Convolutional Neural Networks (CNNs) have gained high popularity as a tool for computer vision tasks and for that reason are used in various applications. There are many different concepts, like single shot detectors, that have been…
Deconvolution is the most commonly used image processing method to remove the blur caused by the point-spread-function (PSF) in optical imaging systems. While this method has been successful in deblurring, it suffers from several…
Object identification is one of the most fundamental and difficult issues in computer vision. It aims to discover object instances in real pictures from a huge number of established categories. In recent years, deep learning-based object…
Convolutional networks are not aware of an object's geometric variations, which leads to inefficient utilization of model and data capacity. To overcome this issue, recent works on deformation modeling seek to spatially reconfigure the data…
In this paper, a scalable neural network hardware architecture for image segmentation is proposed. By sharing the same computing resources, both convolution and deconvolution operations are handled by the same process element array. In…
Fast methods for convolution and correlation underlie a variety of applications in computer vision and graphics, including efficient filtering, analysis, and simulation. However, standard convolution and correlation are inherently limited…
Deformable convolution networks (DCNs) proposed to address the image recognition with geometric or photometric variations typically involve deformable convolution that convolves on arbitrary locations of input features. The locations change…
Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through RANSAC-based algorithms or by directly regressing the pose with end-to-end…
We present a new efficient OpenCL-based Accelerator for large scale Convolutional Neural Networks called Fast Inference on FPGAs for Convolution Neural Network (FFCNN). FFCNN is based on a deeply pipelined OpenCL kernels architecture. As…
This paper demonstrates a practical method that can correct spatial varying blur from a set of images of the same object. The algorithm jointly estimates the object and local point spread functions~(PSF). The method prioritizes sections…
Neuroevolution is a powerful method of applying an evolutionary algorithm to refine the performance of artificial neural networks through natural selection; however, the fitness evaluation of these networks can be time-consuming and…
Deformable image registration poses a challenging problem where, unlike most deep learning tasks, a complex relationship between multiple coordinate systems has to be considered. Although data-driven methods have shown promising…
This paper tackles the problem of dynamic scene deblurring. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is still…
Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendly processing. However, dense pillar processing fundamentally…
In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…