Essays about: "ImageNet"

Showing result 16 - 20 of 48 essays containing the word ImageNet.

  1. 16. Robustness of Image Classification Using CNNs in Adverse Conditions

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Theo Ingelstam; Johanna Skåntorp; [2022]
    Keywords : image recognition; convolutional neural network; CNN; adverse conditions; computer vision; MAdWeather dataset;

    Abstract : The usage of convolutional neural networks (CNNs) has revolutionized the field of computer vision. Though the algorithms used in image recognition have improved significantly in the past decade, they are still limited by the availability of training data. READ MORE

  3. 17. Structural Comparison of Data Representations Obtained from Deep Learning Models

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Tommy Wallin; [2022]
    Keywords : Representation Learning; Deep learning models; Image Representations.; Representationsinlärning; Djupinlärningsmodeller; Bildrepresentationer;

    Abstract : In representation learning we are interested in how data is represented by different models. Representations from different models are often compared by training a new model on a downstream task using the representations and testing their performance. READ MORE

  4. 18. Benchmarking Object Detection Algorithms for Optical Character Recognition of Odometer Mileage

    University essay from Uppsala universitet/Institutionen för informationsteknologi

    Author : Mandus Hjelm; Eric Andersson; [2022]
    Keywords : Computer vision; machine learning; neural networks; object detection; optical character recognition; odometer; transfer learning;

    Abstract : Machine learning algorithms have had breakthroughs in many areas in the last decades. The hardest task, to solve with machine learning, was solving tasks that humans solve intuitively, e.g. understanding natural language or recognizing specific objects in images. READ MORE

  5. 19. Narrow Pretraining of Deep Neural Networks : Exploring Autoencoder Pretraining for Anomaly Detection on Limited Datasets in Non-Natural Image Domains

    University essay from Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakulteten

    Author : Matilda Eriksson; Astrid Johansson; [2022]
    Keywords : CNN; convolutional neural network; autoencoder; variational autoencoder; anomaly detection; SPADE; limited dataset; non-natural image domain; depth domain; scatter domain; intensity domain; machine learning;

    Abstract : Anomaly detection is the process of detecting samples in a dataset that are atypical or abnormal. Anomaly detection can for example be of great use in an industrial setting, where faults in the manufactured products need to be detected at an early stage. READ MORE

  6. 20. Learning from 3D generated synthetic data for unsupervised anomaly detection

    University essay from Uppsala universitet/Avdelningen för visuell information och interaktion

    Author : Hampus Fröjdholm; [2021]
    Keywords : machine learning; synthetic data; anomaly detection; physically based rendering; maskininlärning; syntetisk data; anomalidetektion;

    Abstract : Modern machine learning methods, utilising neural networks, require a lot of training data. Data gathering and preparation has thus become a major bottleneck in the machine learning pipeline and researchers often use large public datasets to conduct their research (such as the ImageNet [1] or MNIST [2] datasets). READ MORE