Generalized zero-shot object recognition withoutclass-attribute relations

Download

12626239.pdf

Date

2021-2-11

Author

Er, Müslüm

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

219
views

264
downloads

Over the last decade, great improvements have been achieved in image classifica-tion performances following the advances in supervised deep learning approaches.These supervised approaches, however, typically require substantial amounts of la-beled training examples. Collecting and annotating such examples is a cumbersomeand error-prone task, especially when a large number of classes needs to be spanned.One of the promising approaches towards overcoming this limitation of supervisedrecognition techniques is zero-shot learning. Inspired by the abilities of human vi-sion, zero-shot learning aims to enable recognition of novel object categories purelybased on category-wide information, which we refer to asauxiliary class information.A more modern variant, called generalized zero-shot learning, aims to build modelsthat can accurately classify novel samples of not only zero-shot classes but also thosewith supervised training examples. Most of the recent generalized zero-shot learningapproaches rely on attribute based auxiliary class information, where the attributescharacterising each class of interest needs to be defined by an oracle. In practice,this dependency greatly reduces the practicality of zero-shot learning as it is oftendifficult to define such class-attribute relationships. To bypass this requirement, in this thesis, we propose a model that requires only class names of novel classes andimplicitly learnspseudo-attributesin an end-to-end manner purely based on a set ofcandidate pseudo-attribute word embeddings. Such word embeddings are much eas-ier to collect than class-attribute annotations, as one can easily select and utilize a setof relevant words from a pre-trained language model that provides vector-space wordembeddings. Additionally, we propose a simple contrastive loss term for improvinggeneralized zero-shot learning based on simple class-to-class name similarity scores.Our experimental results show that the proposed approach yields state-of-the-art classname based generalized zero-shot learning.

Subject Keywords

Generalized Zero-Shot Learning, Contrastive loss, Pseudo-attributes, Word representations

URI

https://hdl.handle.net/11511/89793

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Closed-form sample probing for training generative models in zero-shot learning Çetin, Samet; Cinbiş, Ramazan Gökberk; Department of Computer Engineering (2022-2-10) Generative modeling based approaches have led to significant advances in generalized zero-shot learning over the past few-years. These approaches typically aim to learn a conditional generator that synthesizes training samples of classes conditioned on class embeddings, such as attribute based class definitions. The final zero-shot learning model can then be obtained by training a supervised classification model over the real and/or synthesized training samples of seen and unseen classes, combined. Therefor...
Visual Object Tracking with Autoencoder Representations Besbinar, Beril; Alatan, Abdullah Aydın (2016-05-19) Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have recently improved the state of the art in many areas as a virtue of large labeled datasets, increase in the computational power of current hardware and unsupervised training methods. Although such a dataset may not be available for lots of application areas, the representations obtained by the well-designed networks that have a large representation capacity and trained with enough dat...
Detection of clean samples in noisy labelled datasets via analysis of artificially corrupted samples Yıldırım, Botan; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2022-8-22) Recent advances in supervised deep learning methods have shown great successes in image classification but these methods are known to owe their success to massive amount of data with reliable labels. However, constructing large-scale datasets inevitably results with varying levels of label noise which degrades performance of the supervised deep learning based classifiers. In this thesis, we make an analysis of sample selection based label noise robust approaches by providing extensive experimental evaluatio...
Improving classification performance of endoscopic images with generative data augmentation Çağlar, Ümit Mert; Temizel, Alptekin; Department of Modeling and Simulation (2022-2-8) The performance of a supervised deep learning model is highly dependent on the quality and variety of the images in the training dataset. In some applications, it may be impossible to obtain more images. Data augmentation methods have been proven to be successful in increasing the performance of deep learning models with limited data. Recent improvements on Generative Adversarial Networks (GAN) algorithms and structures resulted in improved image quality and diversity and made GAN training possible with lim...
Hierarchical representations for visual object tracking by detection Beşbınar, Beril; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2015) Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have improved the state of the art in many areas such as visual object detection, scene understanding or speech recognition. Rebirth of these fairly old computational models is usually related to the availability of large datasets, increase in the computational power of current hardware and more recently proposed unsupervised training methods that exploit the internal structure of very lar...

Citation Formats

M. Er, “Generalized zero-shot object recognition withoutclass-attribute relations,” M.S. - Master of Science, Middle East Technical University, 2021.