Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Gradient Matching Generative Networks for Zero-Shot Learning
Date
2019-01-01
Author
Sariyildiz, Mert Bulent
Cinbiş, Ramazan Gökberk
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
170
views
0
downloads
Cite This
Zero-shot learning (ZSL) is one of the most promising problems where substantial progress can potentially be achieved through unsupervised learning, due to distributional differences between supervised and zero-shot classes. For this reason, several works investigate the incorporation of discriminative domain adaptation techniques into ZSL, which, however, lead to modest improvements in ZSL accuracy. In contrast, we propose a generative model that can naturally learn from unsupervised examples, and synthesize training examples for unseen classes purely based on their class embeddings, and therefore, reduce the zero-shot learning problem into a supervised classification task. The proposed approach consists of two important components: (i) a conditional Generative Adversarial Network that learns to produce samples that mimic the characteristics of unsupervised data examples, and (ii) the Gradient Matching (GM) loss that measures the quality of the gradient signal obtained from the synthesized examples. Using our GM loss formulation, we enforce the generator to produce examples from which accurate classifiers can be trained. Experimental results on several ZSL benchmark datasets show that our approach leads to significant improvements over the state of the art in generalized zero-shot classification.
Subject Keywords
Computer science
,
Zero-shot learning (ZSL)
,
Generative adversarial network
,
Gradient Matching (GM)
URI
https://hdl.handle.net/11511/39265
DOI
https://doi.org/10.1109/cvpr.2019.00227
Collections
Department of Computer Engineering, Conference / Seminar
Suggestions
OpenMETU
Core
Simple and complex behavior learning using behavior hidden Markov model and CobART
Seyhan, Seyit Sabri; Alpaslan, Ferda Nur; Yavaş, Mustafa (2013-03-01)
This paper proposes behavior learning and generation models for simple and complex behaviors of robots using unsupervised learning methods. While the simple behaviors are modeled by simple-behavior learning model (SBLM), complex behaviors are modeled by complex-behavior learning model (CBLM) which uses previously learned simple or complex behaviors. Both models include behavior categorization, behavior modeling, and behavior generation phases. In the behavior categorization phase, sensory data are categoriz...
Simple and complex behavior learning using behavior hidden Markov Model and CobART
Seyhan, Seyit Sabri; Alpaslan, Ferda Nur; Department of Computer Engineering (2013)
In this thesis, behavior learning and generation models are proposed for simple and complex behaviors of robots using unsupervised learning methods. Simple behaviors are modeled by simple-behavior learning model (SBLM) and complex behaviors are modeled by complex-behavior learning model (CBLM) which uses previously learned simple or complex behaviors. Both models have common phases named behavior categorization, behavior modeling, and behavior generation. Sensory data are categorized using correlation based...
Attention mechanisms for semantic few-shot learning
Baran, Orhun Buğra; Cinbiş, Ramazan Gökberk; İkizler-Cinbiş, Nazlı; Department of Computer Engineering (2021-9-1)
One of the fundamental difficulties in contemporary supervised learning approaches is the dependency on labelled examples. Most state-of-the-art deep architectures, in particular, tend to perform poorly in the absence of large-scale annotated training sets. In many practical problems, however, it is not feasible to construct sufficiently large training sets, especially in problems involving sensitive information or consisting of a large set of fine-grained classes. One of the main topics in machine learning...
Decision fusion for supervised, unsupervised and semi-supervised learnings
Özay, Mete; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2013)
In this thesis, Decision Fusion approaches have been analyzed for Supervised, Unsupervised and Semi-supervised Learning problems. In Supervised Learning, classification or generalization error minimization problem has been studied by analyzing the classification error of a classification algorithm into two parts. In the first part, the minimization of the difference between N-sample and large-sample classification error of k-NN has been studied using a hierarchical decision fusion algorithm called Fuzzy Sta...
Computational representation of protein sequences for homology detection and classification
Oğul, Hasan; Mumcuoğlu, Ünal Erkan; Department of Information Systems (2006)
Machine learning techniques have been widely used for classification problems in computational biology. They require that the input must be a collection of fixedlength feature vectors. Since proteins are of varying lengths, there is a need for a means of representing protein sequences by a fixed-number of features. This thesis introduces three novel methods for this purpose: n-peptide compositions with reduced alphabets, pairwise similarity scores by maximal unique matches, and pairwise similarity scores by...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
M. B. Sariyildiz and R. G. Cinbiş, “Gradient Matching Generative Networks for Zero-Shot Learning,” 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/39265.