Viso.ai

NOVEMBER 5, 2024

The YOLO Family of Models The first YOLO model was introduced back in 2016 by a team of researchers, marking a significant advancement in object detection technology. They categorized these experiments as Bag of Freebies (BoF) and Bag of Specials (BoS). However, accuracy was poorer compared to two-stage models such as Faster RCNN.

Convolutional Neural Networks 98

Convolutional Neural Networks Neural Network Categorization Automation 98

Viso.ai

DECEMBER 3, 2023

Hence, rapid development in deep convolutional neural networks (CNN) and GPU’s enhanced computing power are the main drivers behind the great advancement of computer vision based object detection. Various two-stage detectors include region convolutional neural network (RCNN), with evolutions Faster R-CNN or Mask R-CNN.

Convolutional Neural Networks 98

Convolutional Neural Networks Computer Vision Neural Network Deep Learning 98

PyImageSearch

NOVEMBER 13, 2023

You’ll typically find IoU and mAP used to evaluate the performance of HOG + Linear SVM detectors ( Dalal and Triggs, 2005 ), Convolutional Neural Network methods, such as Faster R-CNN ( Girshick et al., 2015 ; Redmon and Farhad, 2016 ), and others. 2015 ), SSD ( Fei-Fei et al., 2015 ; He et al., MobileNets ).

Convolutional Neural Networks 117

Convolutional Neural Networks Neural Network Computer Vision Deep Learning 117

Viso.ai

OCTOBER 7, 2024

billion tons of municipal solid waste was generated globally in 2016 with experts predicting a steep rise to 3.40 Object Detection : Computer vision algorithms, such as convolutional neural networks (CNNs), analyze the images to identify and classify waste types (i.e., As per the World Bank, 2.01 billion tons in 2050.

Convolutional Neural Networks 52

Convolutional Neural Networks Computer Vision Neural Network Robotics 52

Explosion

NOVEMBER 9, 2016

2016) introduce an attention mechanism that takes two sentence matrices, and outputs a single vector: Yang et al. 2016) introduce an attention mechanism that takes a single matrix and outputs a single vector. 2016) presented a model that achieved 86.8% 2016) presented a model that achieved 86.8% 2016) HN-ATT 68.2

Deep Learning 52

Deep Learning NLP Convolutional Neural Networks Neural Network 52

Viso.ai

DECEMBER 6, 2024

2016) introduced a unified framework to detect both cyclists and pedestrians from images. Autonomous Driving applying Semantic Segmentation in autonomous vehicles Semantic segmentation is now more accurate and efficient thanks to deep learning techniques that utilize neural network models.

Computer Vision 52

Computer Vision Convolutional Neural Networks Neural Network Deep Learning 52

Snorkel AI

MARCH 1, 2023

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Radford et al. 2016) This paper introduced DCGANs, a type of generative model that uses convolutional neural networks to generate images with high fidelity. Attention Is All You Need Vaswani et al.

BERT 83

BERT Natural Language Processing Large Language Models Neural Network 83