Pooling methods in deep neural networks, a review
H Gholamalinezhad, H Khosravi - arXiv preprint arXiv:2009.07485, 2020 - arxiv.org
Nowadays, Deep Neural Networks are among the main tools used in various sciences.
Convolutional Neural Network is a special type of DNN consisting of several convolution …
Convolutional Neural Network is a special type of DNN consisting of several convolution …
Full-resolution residual networks for semantic segmentation in street scenes
Semantic image segmentation is an essential component of modern autonomous driving
systems, as an accurate understanding of the surrounding scene is crucial to navigation and …
systems, as an accurate understanding of the surrounding scene is crucial to navigation and …
Face alignment across large poses: A 3d solution
Face alignment, which fits a face model to an image and extracts the semantic meanings of
facial pixels, has been an important topic in CV community. However, most algorithms are …
facial pixels, has been an important topic in CV community. However, most algorithms are …
Superpixels: An evaluation of the state-of-the-art
Superpixels group perceptually similar pixels to create visually meaningful entities while
heavily reducing the number of primitives for subsequent processing steps. As of these …
heavily reducing the number of primitives for subsequent processing steps. As of these …
T-cnn: Tubelets with convolutional neural networks for object detection from videos
The state-of-the-art performance for object detection has been significantly improved over
the past two years. Besides the introduction of powerful deep neural networks, such as …
the past two years. Besides the introduction of powerful deep neural networks, such as …
Densebox: Unifying landmark localization with end to end object detection
How can a single fully convolutional neural network (FCN) perform on object detection? We
introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding …
introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding …
Superpixel sampling networks
Superpixels provide an efficient low/mid-level representation of image data, which greatly
reduces the number of image primitives for subsequent vision tasks. Existing superpixel …
reduces the number of image primitives for subsequent vision tasks. Existing superpixel …
Learning non-maximum suppression
J Hosang, R Benenson… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Object detectors have hugely profited from moving towards an end-to-end learning
paradigm: proposals, fea tures, and the classifier becoming one neural network improved …
paradigm: proposals, fea tures, and the classifier becoming one neural network improved …
Real-time superpixel segmentation by DBSCAN clustering algorithm
In this paper, we propose a real-time image superpixel segmentation method with 50
frames/s by using the density-based spatial clustering of applications with noise (DBSCAN) …
frames/s by using the density-based spatial clustering of applications with noise (DBSCAN) …
Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds
Extracting ships from complex backgrounds is the bottleneck of ship detection in high-
resolution optical satellite images. In this letter, we propose a nearly closed-form ship rotated …
resolution optical satellite images. In this letter, we propose a nearly closed-form ship rotated …