Generalized Zero-Shot Learning through Similarity Distribution Matching
| dc.contributor.advisor | Shrivastava, Anshumali | en_US |
| dc.creator | Daghaghi, Shabnam | en_US |
| dc.date.accessioned | 2022-10-05T21:44:55Z | en_US |
| dc.date.available | 2022-10-05T21:44:55Z | en_US |
| dc.date.created | 2022-05 | en_US |
| dc.date.issued | 2022-02-18 | en_US |
| dc.date.submitted | May 2022 | en_US |
| dc.date.updated | 2022-10-05T21:44:56Z | en_US |
| dc.description.abstract | Recent advances in supervised learning methods in vision, specifically deep learning frameworks, are primarily built on the abundance of labeled images. However, image labeling is a laborious task, therefore many visual categories are unlabeled or even unavailable. Zero-Shot Learning (ZSL) deals with classifying unseen visual categories that have no samples during training phase. In particular, ZSL is a classification task where some classes referred to as unseen classes have no training images. Instead, we only have side information about seen and unseen classes, often in the form of semantic or descriptive attributes. Lack of training images from a set of classes restricts the use of standard classification techniques and losses, including the widespread cross-entropy loss. We introduce a novel Similarity Distribution Matching Network (SDM-Net) which is a standard fully connected neural-network architecture with non-trainable penultimate layer consisting of class attributes. The output layer of SDM-Net consists of both seen and unseen classes. To enable zero-shot learning, during training, we regularize the model such that the predicted distribution of unseen class is close in KL divergence to the distribution of similarities between the correct seen class and all the unseen classes. We evaluate the proposed model on five benchmark datasets for zero-shot learning, AwA1, AwA2, aPY, SUN and CUB datasets. We show that, despite the simplicity, our approach achieves competitive performance with state-of-the-art methods in Generalized-ZSL setting for all of these datasets. | en_US |
| dc.format.mimetype | application/pdf | en_US |
| dc.identifier.citation | Daghaghi, Shabnam. "Generalized Zero-Shot Learning through Similarity Distribution Matching." (2022) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/113538">https://hdl.handle.net/1911/113538</a>. | en_US |
| dc.identifier.uri | https://hdl.handle.net/1911/113538 | en_US |
| dc.language.iso | eng | en_US |
| dc.rights | Copyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder. | en_US |
| dc.subject | Generalized Zero-Shot Learning | en_US |
| dc.subject | Image Classification | en_US |
| dc.subject | Semantic Similarity | en_US |
| dc.subject | KL Divergence | en_US |
| dc.title | Generalized Zero-Shot Learning through Similarity Distribution Matching | en_US |
| dc.type | Thesis | en_US |
| dc.type.material | Text | en_US |
| thesis.degree.department | Electrical and Computer Engineering | en_US |
| thesis.degree.discipline | Engineering | en_US |
| thesis.degree.grantor | Rice University | en_US |
| thesis.degree.level | Masters | en_US |
| thesis.degree.name | Master of Science | en_US |
Files
Original bundle
1 - 1 of 1