Learning efficient visual embedding models under data constraints
Author(s)
Advisor
Aksoy, SelimDate
2019-09Publisher
Bilkent University
Language
English
Type
ThesisItem Usage Stats
287
views
views
318
downloads
downloads
Abstract
Deep learning models require large-scale datasets to learn rich sets of low and
mid-level patterns and high-level semantics. Therefore, given a high-capacity
neural network, one way to improve the performance of a model is increasing the
size of the dataset which the model is trained over on. Considering that it is easy
to get the amount of computational power required to train a network, data becomes
a serious bottleneck in scaling up the existing machine learning pipelines.
In this thesis, we look into two main data bottlenecks that rise in computer vision
applications: I. the difficulty of finding training data for diverse sets of object categories,
II. the complication of utilizing data containing sensitive user information
for the purpose of training neural network models. To address these issues, we
study zero-shot learning and decentralized learning schemes, respectively.
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.
Collaborative learning techniques provide a privacy-preserving solution, by
enabling training over a number of private datasets that are not shared by their
owners. However, recently, it has been shown that the existing collaborative
learning frameworks are vulnerable to an active adversary that runs a generative
adversarial network (GAN) attack. In this work, we propose a novel classification
model that is resilient against such attacks by design. More specifically,
we introduce a key-based classification model and a principled training scheme
that protects class scores by using class-specific private keys, which effectively
hides the information necessary for a GAN attack. We additionally show how
to utilize high dimensional keys to improve the robustness against attacks without
increasing the model complexity. Our detailed experiments demonstrate the
effectiveness of the proposed technique.
Keywords
Zero-shot learningMeta learning
Generative models
Privacypreserving machine learning
Collaborative learning
Cassification, generative adversarial networks
Permalink
http://hdl.handle.net/11693/52409Collections
Related items
Showing items related by title, author, creator and subject.
-
Adaptive ensemble learning with confidence bounds for personalized diagnosis
Tekin, Cem; Yoon, J.; Van Der Schaar, M. (AAAI Press, 2016)With the advances in the field of medical informatics, automated clinical decision support systems are becoming the de facto standard in personalized diagnosis. In order to establish high accuracy and confidence in ... -
The effect of uncertainty on learning in game-like environments
Ozcelik, E.; Cagiltay, N. E.; Ozcelik, N. S. (Pergamon Press, 2013)Considering the role of games for educational purposes, there has an increase in interest among educators in applying strategies used in popular games to create more engaging learning environments. Learning is more fun and ... -
Big-data streaming applications scheduling based on staged multi-armed bandits
Kanoun, K.; Tekin, C.; Atienza, D.; Van Der Schaar, M. (Institute of Electrical and Electronics Engineers, 2016)Several techniques have been recently proposed to adapt Big-Data streaming applications to existing many core platforms. Among these techniques, online reinforcement learning methods have been proposed that learn how to ...