Learning equivariant representations / Carlos Henrique Machado Silva Esteves.

Format:

Book

Thesis/Dissertation

Author/Creator:

Silva Esteves, Carlos Henrique Machado, author.

Contributor:

Daniilidis, Kostas, degree supervisor.

University of Pennsylvania. Department of Computer and Information Science, degree granting institution.

Language:

English

Subjects (All):

Artificial intelligence.

Computer science.

Applied mathematics.

Computer and Information Science--Penn dissertations.

Penn dissertations--Computer and Information Science.

Local Subjects:

Artificial intelligence.

Computer science.

Applied mathematics.

Computer and Information Science--Penn dissertations.

Penn dissertations--Computer and Information Science.

Genre:

Academic theses.

Physical Description:

1 online resource (261 pages)

Contained In:

Dissertations Abstracts International 82-08B.

Place of Publication:

[Philadelphia, Pennsylvania] : University of Pennsylvania ; Ann Arbor : ProQuest Dissertations & Theses, 2020.

Language Note:

English

System Details:

Mode of access: World Wide Web.

text file

Summary:

State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of this principle, their defining characteristic being the shift-equivariance. By sliding a filter over the input, when the input shifts, the response shifts by the same amount, exploiting the structure of natural images where semantic content is independent of absolute pixel positions. This property is essential to the success of CNNs in audio, image and video recognition tasks. In this thesis, we extend equivariance to other kinds of transformations, such as rotation and scaling. We propose equivariant models for different transformations defined by groups of symmetries. The main contributions are (i) polar transformer networks, achieving equivariance to the group of similarities on the plane, (ii) equivariant multi-view networks, achieving equivariance to the group of symmetries of the icosahedron, (iii) spherical CNNs, achieving equivariance to the continuous 3D rotation group, (iv) cross-domain image embeddings, achieving equivariance to 3D rotations for 2D inputs, and (v) spin-weighted spherical CNNs, generalizing the spherical CNNs and achieving equivariance to 3D rotations for spherical vector fields. Applications include image classification, 3D shape classification and retrieval, panoramic image classification and segmentation, shape alignment and pose estimation. What these models have in common is that they leverage symmetries in the data to reduce sample and model complexity and improve generalization performance. The advantages are more significant on (but not limited to) challenging tasks where data is limited or input perturbations such as arbitrary rotations are present.

Notes:

Source: Dissertations Abstracts International, Volume: 82-08, Section: B.

Advisors: Daniilidis, Kostas; Committee members: Jean Gallier; Jianbo Shi; Alejandro Ribeiro; Ameesh Makadia.

Department: Computer and Information Science.

Ph.D. University of Pennsylvania 2020.

Local Notes:

School code: 0175

ISBN:

9798557075251

Access Restriction:

Restricted for use by site license.

This item must not be sold to any third party vendors.