Performance Analysis of Deep Neural Networks Using Computer Vision

AbstractDeep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning methods compared to the causal, hypothesis driven nature of modern science. We argue that the broad adoption of Bayesian methods incorporating prior knowledge, development of solutions with incorporated physical constraints and parsimonious structural descriptors and generative models, and ultimately adoption of causal models, offers a path forward for fundamental and applied research.

Download Full-text

Deep neural networks only in combination with traditional computer vision

ATZelektronik worldwide ◽

10.1007/s38314-017-0077-3 ◽

2017 ◽

Vol 12 (6) ◽

pp. 26-31

Author(s):

Uwe Westmeyer

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Deep Neural Networks

Download Full-text

Survey on Energy-Efficient Deep Neural Networks for Computer Vision

Low-Power Computer Vision ◽

10.1201/9781003162810-3 ◽

2022 ◽

pp. 25-52

Author(s):

Abhinav Goel ◽

Caleb Tung ◽

Xiao Hu ◽

Haobo Wang ◽

Yung-Hsiang Lu ◽

...

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Energy Efficient ◽

Deep Neural Networks

Download Full-text

Comparative Performance Analysis of Neural Network Real-Time Object Detections in Different Implementations

EPJ Web of Conferences ◽

10.1051/epjconf/202022602020 ◽

2020 ◽

Vol 226 ◽

pp. 02020

Author(s):

Alexey V. Stadnik ◽

Pavel S. Sazhin ◽

Slavomir Hnatic

Keyword(s):

Neural Network ◽

Neural Networks ◽

Computer Vision ◽

Performance Analysis ◽

Object Detection ◽

Real Time ◽

Network Architecture ◽

Neural Network Architecture ◽

Comparative Performance

The performance of neural networks is one of the most important topics in the field of computer vision. In this work, we analyze the speed of object detection using the well-known YOLOv3 neural network architecture in different frameworks under different hardware requirements. We obtain results, which allow us to formulate preliminary qualitative conclusions about the feasibility of various hardware scenarios to solve tasks in real-time environments.

Download Full-text

Technical note: AI-Track-tive: automated fission track recognition using computer vision (Artificial Intelligence)

10.5194/gchron-2020-32 ◽

2020 ◽

Author(s):

Simon Nachtergaele ◽

Johan De Grave

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

Computer Vision ◽

Deep Neural Networks ◽

Fission Track ◽

Detection Algorithm ◽

Technical Note ◽

Success Rates ◽

Automatic Counting ◽

First Time

Abstract. Artificial intelligence techniques such as deep neural networks and computer vision are developed for fission track recognition and included in a computer program for the first time. These deep neural networks use the Yolov3 object detection algorithm, which is currently one of the most powerful and fastest object recognition algorithms. These deep neural networks can be used in new software called AI-Track-tive. The developed program successfully finds most of the fission tracks in the microscope images, however, the user still needs to supervise the automatic counting. The success rates of the automatic recognition range from 70 % to 100 % depending on the areal track densities in apatite and (muscovite) external detector. The success rate generally decreases for images with high areal track densities, because overlapping tracks are less easily recognizable for computer vision techniques.

Download Full-text

Avaliação do Processo para Embarcar uma Rede Neural Baseada em YOLO Utilizando um Acelerador de Hardware Dedicado

10.5753/sbesc_estendido.2020.13109 ◽

2020 ◽

Author(s):

Isabel Costa ◽

Elias Silva Jr ◽

Antônio Rodrigues ◽

Leandro Angeloni ◽

Edmilson Dias

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Object Detection ◽

Power Distribution ◽

Deep Neural Networks ◽

Aerial Images ◽

Great Progress ◽

Operational Networks

Object Detection is a challenging task in computer vision, but Deep Neural Networks (DNN) have made great progress in this area. This work presents the process and the results obtained in the attempts to embed a YOLO V3 model in a Neural Compute Engine, the Movidius Stick. Experiments were carried out with a Tensorflow model that is converted to Movidius (using OpenVINO) including an evaluation of the Movidius stick connected to a Raspberry Pi3. The application uses aerial images of power distribution towers captured by a drone. Although there are some fully operational networks for Neural Compute Engines, there are some difficulties in porting new networks to the platform, with gains in performance, but with losses in accuracy.

Download Full-text

Vision beyond Pixels: Visual Reasoning via Blocksworld Abstractions

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/907 ◽

2019 ◽

Author(s):

Tejas Gokhale

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Cognitive Psychology ◽

Visual Perception ◽

Deep Neural Networks ◽

Natural Images ◽

Modular Approach ◽

Reasoning Task ◽

Two Stages ◽

Event Sequencing

Deep neural networks trained in an end-to-end fashion have brought about exceptional advances in computer vision, especially in computational perception. We go beyond perception and seek to enable vision modules to reason about perceived visual entities such as scenes, objects and actions. We introduce a challenging visual reasoning task, Image-Based Event Sequencing (IES) and compile the first IES dataset, Blocksworld Image Reasoning Dataset (BIRD). Motivated by the blocksworld concept, we propose a modular approach supported by literature in cognitive psychology and children's development. We decompose the problem into two stages - visual perception and event sequencing, and show that our approach can be extended to natural images without re-training.

Download Full-text

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Machine Learning and Knowledge Extraction ◽

10.3390/make3040048 ◽

2021 ◽

Vol 3 (4) ◽

pp. 966-989

Author(s):

Vanessa Buhrmester ◽

David Münch ◽

Michael Arens

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Deep Neural Networks ◽

State Of The Art ◽

Black Box ◽

Complex Data ◽

Comprehensive Overview ◽

Nonlinear Structure ◽

Black Boxes ◽

Insight Into

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.

Download Full-text

Multimodal Multi-tasking for Skin Lesion Classification Using Deep Neural Networks

10.1007/978-3-030-90439-5_3 ◽

2021 ◽

pp. 27-38

Author(s):

Rafaela Carvalho ◽

João Pedrosa ◽

Tudor Nedelcu

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Deep Learning ◽

Skin Lesion ◽

Deep Neural Networks ◽

Classification Performance ◽

Additional Information ◽

Deep Learning Model ◽

Lesion Classification

AbstractSkin cancer is one of the most common types of cancer and, with its increasing incidence, accurate early diagnosis is crucial to improve prognosis of patients. In the process of visual inspection, dermatologists follow specific dermoscopic algorithms and identify important features to provide a diagnosis. This process can be automated as such characteristics can be extracted by computer vision techniques. Although deep neural networks can extract useful features from digital images for skin lesion classification, performance can be improved by providing additional information. The extracted pseudo-features can be used as input (multimodal) or output (multi-tasking) to train a robust deep learning model. This work investigates the multimodal and multi-tasking techniques for more efficient training, given the single optimization of several related tasks in the latter, and generation of better diagnosis predictions. Additionally, the role of lesion segmentation is also studied. Results show that multi-tasking improves learning of beneficial features which lead to better predictions, and pseudo-features inspired by the ABCD rule provide readily available helpful information about the skin lesion.

Download Full-text

A new strategy for curriculum learning using model distillation

Global Journal of Computer Sciences Theory and Research ◽

10.18844/gjcs.v10i2.5810 ◽

2020 ◽

Vol 10 (2) ◽

pp. 57-65

Author(s):

Kaan Karakose ◽

Metin Bilgin

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Artificial Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

Mixed Data ◽

Training Set ◽

Complex Samples ◽

New Strategy ◽

Sample Sorting

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. Humans and animals learn much better when gradually presented in a meaningful order showing more concepts and complex samples rather than randomly presenting the information. The use of such training strategies in the context of artificial neural networks is called curriculum learning. In this study, a strategy was developed for curriculum learning. Using the CIFAR-10 and CIFAR-100 training sets, the last few layers of the pre-trained on ImageNet Xception model were trained to keep the training set knowledge in the model’s weight. Finally, a much smaller model was trained with the sample sorting methods presented using these difficulty levels. The findings obtained in this study show that the accuracy value generated when trained by the method we provided with the accuracy value trained with randomly mixed data was more than 1% for each epoch. Keywords: Curriculum learning, model distillation, deep learning, academia, neural networks.

Download Full-text