Object detection in 20 years: A survey
Object detection, as of one the most fundamental and challenging problems in computer
vision, has received great attention in recent years. Over the past two decades, we have …
vision, has received great attention in recent years. Over the past two decades, we have …
[HTML][HTML] A review on modern defect detection models using DCNNs–Deep convolutional neural networks
Background Over the last years Deep Learning has shown to yield remarkable results when
compared to traditional computer vision algorithms, in a large variety of computer vision …
compared to traditional computer vision algorithms, in a large variety of computer vision …
A crossbar array of magnetoresistive memory devices for in-memory computing
Implementations of artificial neural networks that borrow analogue techniques could
potentially offer low-power alternatives to fully digital approaches,–. One notable example is …
potentially offer low-power alternatives to fully digital approaches,–. One notable example is …
Logic-in-memory based on an atomically thin semiconductor
The growing importance of applications based on machine learning is driving the need to
develop dedicated, energy-efficient electronic hardware. Compared with von Neumann …
develop dedicated, energy-efficient electronic hardware. Compared with von Neumann …
YOLOv4-5D: An effective and efficient object detector for autonomous driving
Y Cai, T Luan, H Gao, H Wang, L Chen… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
The use of object detection algorithms has become extremely important in autonomous
vehicles. Object detection at high accuracy and a fast inference speed is essential for safe …
vehicles. Object detection at high accuracy and a fast inference speed is essential for safe …
Squeezesegv3: Spatially-adaptive convolution for efficient point-cloud segmentation
LiDAR point-cloud segmentation is an important problem for many applications. For large-
scale point cloud segmentation, the de facto method is to project a 3D point cloud to get a …
scale point cloud segmentation, the de facto method is to project a 3D point cloud to get a …
Fbnetv2: Differentiable neural architecture search for spatial and channel dimensions
Abstract Differentiable Neural Architecture Search (DNAS) has demonstrated great success
in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's …
in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's …
Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges
Recent advancements in perception for autonomous driving are driven by deep learning. In
order to achieve robust and accurate scene understanding, autonomous vehicles are …
order to achieve robust and accurate scene understanding, autonomous vehicles are …
Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search
Designing accurate and efficient ConvNets for mobile devices is challenging because the
design space is combinatorially large. Due to this, previous neural architecture search (NAS) …
design space is combinatorially large. Due to this, previous neural architecture search (NAS) …
Disentangling monocular 3d object detection
In this paper we propose an approach for monocular 3D object detection from a single RGB
image, which leverages a novel disentangling transformation for 2D and 3D detection losses …
image, which leverages a novel disentangling transformation for 2D and 3D detection losses …