Performance Evaluation of Deep Learning frameworks on Computer Vision problems

2019 ◽  
Author(s):  
Madhumitha Nara ◽  
B R Mukesh ◽  
Preethi Padala ◽  
Bharath Kinnal
Keyword(s):  
Computer Vision ◽  
Performance Evaluation ◽  
Deep Learning ◽  
Learning Frameworks

scholarly journals Content Fidelity of Deep Learning Methods for Clipping and Over-exposure Correction

2021 ◽  
Vol 2021 (1) ◽  
pp. 43-48
Author(s):  
Mekides Assefa Abebe
Keyword(s):  
Computer Vision ◽  
Performance Evaluation ◽  
Deep Learning ◽  
Generative Adversarial Networks ◽  
Tone Mapping ◽  
Objective Functions ◽  
Related Research ◽  
Adversarial Networks ◽  
Computer Vision Applications ◽  
Research Domains

Exposure problems, due to standard camera sensor limitations, often lead to image quality degradations such as loss of details and change in color appearance. The quality degradations further hiders the performances of imaging and computer vision applications. Therefore, the reconstruction and enhancement of uderand over-exposed images is essential for various applications. Accordingly, an increasing number of conventional and deep learning reconstruction approaches have been introduced in recent years. Most conventional methods follow color imaging pipeline, which strongly emphasize on the reconstructed color and content accuracy. The deep learning (DL) approaches have conversely shown stronger capability on recovering lost details. However, the design of most DL architectures and objective functions don’t take color fidelity into consideration and, hence, the analysis of existing DL methods with respect to color and content fidelity will be pertinent. Accordingly, this work presents performance evaluation and results of recent DL based overexposure reconstruction solutions. For the evaluation, various datasets from related research domains were merged and two generative adversarial networks (GAN) based models were additionally adopted for tone mapping application scenario. Overall results show various limitations, mainly for severely over-exposed contents, and a promising potential for DL approaches, GAN, to reconstruct details and appearance.

scholarly journals Albumentations: Fast and Flexible Image Augmentations

Information ◽  
2020 ◽  
Vol 11 (2) ◽  
pp. 125 ◽  
Author(s):  
Alexander Buslaev ◽  
Vladimir I. Iglovikov ◽  
Eugene Khvedchenya ◽  
Alex Parinov ◽  
Mikhail Druzhinin ◽  
...  
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Processing Speed ◽  
Data Augmentation ◽  
Improve Performance ◽  
Regularization Technique ◽  
Image Transform ◽  
Basic Image ◽  
Learning Frameworks ◽  
Image Transformations

Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve corresponding output labels. In computer vision, image augmentations have become a common implicit regularization technique to combat overfitting in deep learning models and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations of flipping, rotating, scaling, and cropping. Moreover, image processing speed varies in existing image augmentation libraries. We present Albumentations, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries. We discuss the design principles that drove the implementation of Albumentations and give an overview of the key features and distinct capabilities. Finally, we provide examples of image augmentations for different computer vision tasks and demonstrate that Albumentations is faster than other commonly used image augmentation tools on most image transform operations.

Object Recognition Using Deep Learning

2019 ◽  
Vol 16 (9) ◽  
pp. 4044-4052 ◽  
Author(s):  
Rohini Goel ◽  
Avinash Sharma ◽  
Rajiv Kapoor
Keyword(s):  
Neural Network ◽  
Performance Evaluation ◽  
Deep Learning ◽  
Object Recognition ◽  
Deep Neural Network ◽  
Learning Approaches ◽  
Learning Techniques ◽  
Benchmark Datasets ◽  
Learning Frameworks

The deep learning approaches have drawn much focus of the researchers in the area of object recognition because of their implicit strength of conquering the shortcomings of classical approaches dependent on hand crafted features. In the last few years, the deep learning techniques have been made many developments in object recognition. This paper indicates some recent and efficient deep learning frameworks for object recognition. The up to date study on recently developed a deep neural network based object recognition methods is presented. The various benchmark datasets that are used for performance evaluation are also discussed. The applications of the object recognition approach for specific types of objects (like faces, buildings, plants etc.) are also highlighted. We conclude up with the merits and demerits of existing methods and future scope in this area.

scholarly journals Sequence-to-function deep learning frameworks for engineered riboregulators

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Jacqueline A. Valeri ◽  
Katherine M. Collins ◽  
Pradeep Ramesh ◽  
Miguel A. Alcantar ◽  
Bianca A. Lepe ◽  
...  
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Nucleic Acid ◽  
Language Processing ◽  
Training Data ◽  
Design Rules ◽  
Improved Performance ◽  
Circuit Components ◽  
Learning Frameworks ◽  
Learning Architectures

Abstract While synthetic biology has revolutionized our approaches to medicine, agriculture, and energy, the design of completely novel biological circuit components beyond naturally-derived templates remains challenging due to poorly understood design rules. Toehold switches, which are programmable nucleic acid sensors, face an analogous design bottleneck; our limited understanding of how sequence impacts functionality often necessitates expensive, time-consuming screens to identify effective switches. Here, we introduce Sequence-based Toehold Optimization and Redesign Model (STORM) and Nucleic-Acid Speech (NuSpeak), two orthogonal and synergistic deep learning architectures to characterize and optimize toeholds. Applying techniques from computer vision and natural language processing, we ‘un-box’ our models using convolutional filters, attention maps, and in silico mutagenesis. Through transfer-learning, we redesign sub-optimal toehold sensors, even with sparse training data, experimentally validating their improved performance. This work provides sequence-to-function deep learning frameworks for toehold selection and design, augmenting our ability to construct potent biological circuit components and precision diagnostics.

scholarly journals Deep vision pipeline for self-driving cars based on machine learning methods

2021 ◽  
Author(s):  
Mohammed Nabeel Ahmed
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Source Code ◽  
Lessons Learned ◽  
Pipeline Architecture ◽  
Machine Learning Methods ◽  
Self Driving Cars ◽  
Pipeline Design ◽  
Future Work ◽  
Learning Frameworks

The purpose of this thesis project is to design and implement a vision pipeline useful for self-driving cars, based on computer vision methods and deep learning frameworks. This pipeline is useful for identifying the lane, other cars in the view, as well as traffic signs. A final vision pipeline design is proposed that explores a network that can control steering based on vision input. Firstly, the working model of computer vision techniques used are presented. The mathematical models used are explored, and implementation in source code developed. These models comprise the vision side of the pipeline. Secondly, this report explores the deep learning models implemented as part of the pipeline. The mathematical approach is presented as well as the source code implementation. The models are industry and academia proven and their implementation is developed in detail. The final part provides details on full pipeline architecture, and required hardware. A comprehensive discussion is made on the pipeline, the lessons learned, and future work.

scholarly journals Deep vision pipeline for self-driving cars based on machine learning methods

2021 ◽  
Author(s):  
Mohammed Nabeel Ahmed
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Source Code ◽  
Lessons Learned ◽  
Pipeline Architecture ◽  
Machine Learning Methods ◽  
Self Driving Cars ◽  
Pipeline Design ◽  
Future Work ◽  
Learning Frameworks

The purpose of this thesis project is to design and implement a vision pipeline useful for self-driving cars, based on computer vision methods and deep learning frameworks. This pipeline is useful for identifying the lane, other cars in the view, as well as traffic signs. A final vision pipeline design is proposed that explores a network that can control steering based on vision input. Firstly, the working model of computer vision techniques used are presented. The mathematical models used are explored, and implementation in source code developed. These models comprise the vision side of the pipeline. Secondly, this report explores the deep learning models implemented as part of the pipeline. The mathematical approach is presented as well as the source code implementation. The models are industry and academia proven and their implementation is developed in detail. The final part provides details on full pipeline architecture, and required hardware. A comprehensive discussion is made on the pipeline, the lessons learned, and future work.

Sequence-Based Deep Learning Frameworks on Enhancer-Promoter Interactions Prediction

2020 ◽  
Vol 26 ◽  
Author(s):  
Xiaoping Min ◽  
Fengqing Lu ◽  
Chunyan Li
Keyword(s):  
Gene Expression ◽  
Deep Learning ◽  
Dna Sequences ◽  
Experimental Methods ◽  
Learning Methods ◽  
Comprehensive Review ◽  
Genomic Features ◽  
Disease Mechanisms ◽  
Evaluation Strategies ◽  
Learning Frameworks

: Enhancer-promoter interactions (EPIs) in the human genome are of great significance to transcriptional regulation which tightly controls gene expression. Identification of EPIs can help us better deciphering gene regulation and understanding disease mechanisms. However, experimental methods to identify EPIs are constrained by the fund, time and manpower while computational methods using DNA sequences and genomic features are viable alternatives. Deep learning methods have shown promising prospects in classification and efforts that have been utilized to identify EPIs. In this survey, we specifically focus on sequence-based deep learning methods and conduct a comprehensive review of the literatures of them. We first briefly introduce existing sequence-based frameworks on EPIs prediction and their technique details. After that, we elaborate on the dataset, pre-processing means and evaluation strategies. Finally, we discuss the challenges these methods are confronted with and suggest several future opportunities.

Sign in / Sign up

Export Citation Format

Share Document