Essays about: "fine-grained classification problem"

Found 4 essays containing the words fine-grained classification problem.

  1. 1. Keeping tabs on GPT-SWE : Classifying toxic output from generative language models for Swedish text generation

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

    Author : Isak Pettersson; [2022]
    Keywords : Active learning; Classification; Language models; Natural Language Processing; Swedish; Transformers; Toxic text; Aktiv inlärning; Klassificering; Språkmodeller; Språkteknologi; Svenska; Transformer nätverk; Toxisk text;

    Abstract : Disclaimer: This paper contains content that can be perceived as offensive or upsetting. Considerable progress has been made in Artificial intelligence (AI) and Natural language processing (NLP) in the last years. READ MORE

  3. 2. One Stage Fine- Grained Classification

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

    Author : Xing Zeng; [2021]
    Keywords : Finegrained Visual Classification; YOLO; Onestage classifier; Localization.; Finkornad visuell klassificering; YOLO; klassificering i ett steg; lokalisering.;

    Abstract : Fine- grained Visual Classification (FGVC) is a rapidly growing field in image classification. However, it is a challenging task due to subcategories sharing subtle differences. READ MORE

  4. 3. An Investigation of Low-Rank Decomposition for Increasing Inference Speed in Deep Neural Networks With Limited Training Data

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

    Author : Victor Wikén; [2018]
    Keywords : deep neural networks; convolutional neural networks; AlexNet; inference speed; optimization; low-rank tensor decomposition; fine-grained classification problem; dog breed classification; transfer learning;

    Abstract : In this study, to increase inference speed of convolutional neural networks, the optimization technique low-rank tensor decomposition has been implemented and applied to AlexNet which had been trained to classify dog breeds. Due to a small training set, transfer learning was used in order to be able to classify dog breeds. READ MORE

  5. 4. Deep Convolutional Neural Network for Effective Image Analysis : DESIGN AND IMPLEMENTATION OF A DEEP PIXEL-WISE SEGMENTATION ARCHITECTURE

    University essay from KTH/Skolan för informations- och kommunikationsteknik (ICT)

    Author : Marco Ros Marti; [2017]
    Keywords : CNN; Co-CNN; segmentation; localization; RoI; masking; RoI masking; multi-task network; pixel resolution; overfitting; CNN; segmentació; localització; RoI; emmascarar; filtratge de RoIs; xarxa multi-tasca; resolució de píxel; overfitting; CNN; Co-CNN; segmentering; lokalisering; RoI; maskering; RoI- maskering; flera uppgiftsnätverk; pixelupplösning; övermontering;

    Abstract : This master thesis presents the process of designing and implementing a CNN-based architecture for image recognition included in a larger project in the field of fashion recommendation with deep learning. Concretely, the presented network aims to perform localization and segmentation tasks. READ MORE