Diferencijalne deformacije u modelima za klasifikaciju slike

undergraduate thesis

• Title (english): Differentiable deformations for image classification models
• Author: Pavo Matanović
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Committee member: Petra Bevandić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rad daje uvod u umjetne neuronske mreže s naglaskom na konvolucijskim modelima. Ukratko je opisano učenje neuronske mreže. U radu uvodimo dodatni modul za prostornu transformaciju u konvolucijski model, kako bi poboljšali prostornu invarijantnost modela. Opisujemo arhitekturu dodatnog modula te dvije implementirane deformacije - afinu transformaciju i thin-plate spline transformaciju. Dana je programska implementacija modela te metode za učenje i evaluaciju istih. Modeli su trenirani na skupu MNIST. Prikazani su usporedni rezultati dvaju modela s modulom za prostornu transformaciju i modela bez dodatnog modula.

Abstract (english)

This paper gives an introduction to artificial neural networks with emphasis on convolutional models. We described briefly learning process of neural network. In this work we introduce additional spatial transformer module in convolutional model to increase spatial invariance. We describe the architecture of additional module and two implemented deformations -- affine transformation and thin-plate spline transformation. This paper gives code of model in PyTorch and methods for training and testing models. We trained models on MNIST dataset. We gave comparative results of two models with spatial transformations and third model without STN.

• Keywords: Strojno učenje; duboko učenje; duboke neuronske mreže; konvolucijske neuronske mreže; klasifikacija; modul za prostornu transformaciju; afina transformacija; thin-plate spline transformacija; MNIST
• Keywords (english): Machine Learning; Deep Learning; Deep Neural Networks; Convolutional Neural Network; clasification; Spatial Transformer Network; Affine transformation; Thin-Plate Spline transformation; MNIST
• Language: croatian
• URN:NBN: urn:nbn:hr:168:452747
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:29:24