Towards Uncertainty-Aware Disentangled Representations

Download

10425335.pdf

Date

2021-9-09

Author

Özyeğin, Sezai Artun

Metadata

Show full item record

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

Item Usage Stats

390
views

64
downloads

In many computer vision tasks, not every part of an object of interest is always visible because of challenges like occlusion, viewpoint and pose variation. One approach to these kinds of challenges is separating the representation so that they would correspond to different regions. In this thesis, we tackle the problem of obtaining disentangled representations while estimating the uncertainty of each factor to assess its availability. Representations are disentangled using a factor-related supervised task and by using an adversarial loss, unrelated information is removed. Uncertainty of factors are estimated using loss attenuation over the same factor-related task. We try several methods to integrate uncertainty values into both the training procedure and the decision making process during test time to make the model more robust to unavailable parts. The experiments are conducted over a toy dataset and the person re-identification task (namely, the Market-1501 dataset) which can benefit from disentangled representations.

Subject Keywords

Disentanglement, Uncertainty Estimation, Representation Learning, Deep Learning

URI

https://hdl.handle.net/11511/93206

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Shape descriptors based on intersection consistency and global binary patterns Sivri, Erdal; Kalkan, Sinan; Department of Computer Engineering (2012) Shape description is an important problem in computer vision because most vision tasks that require comparing or matching visual entities rely on shape descriptors. In this thesis, two novel shape descriptors are proposed, namely Intersection Consistency Histogram (ICH) and Global Binary Patterns (GBP). The former is based on a local regularity measure called Intersection Consistency (IC), which determines whether edge pixels in an image patch point towards the center or not. The second method, called Globa...
Perceptual quality preserving adversarial attacks Aksoy, Bilgin; Temizel, Alptekin; Department of Modeling and Simulation (2019) Deep learning is used in various succesful computer vision applications such as image classification. Deep neural networks (DNN) especially convolutional neural networks have reached above human level accuracy rates for image classification tasks. While DNNs have solved the image classification task and enabled its use in many practical applications, recent research has unveiled some properties which could degrade their performance. Adversarial images are samples that are intentionally modified by adding no...
Weakly supervised instance attention for multisource fine-grained object recognition with an application to tree species classification Aygunes, Bulut; Cinbiş, Ramazan Gökberk; Aksoy, Selim (2021-06-01) Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories. However, for multisource tasks that involve relatively small objects, even the smallest registration errors can introduce high uncertainty in the classification process. We approach this problem from a weakly supervised learning perspective in which the input images correspond to larger neighborh...
Automated learning rate search using batch-level cross-validation Kabakcı, Duygu; Akbaş, Emre; Department of Computer Engineering (2019) Deep convolutional neural networks are being widely used in computer vision tasks, such as object recognition and detection, image segmentation and face recognition, with a variety of architectures. Deep learning researchers and practitioners have accumulated a significant amount of experience on training a wide variety of architectures on various datasets. However, given a specific network model and a dataset, obtaining the best model (i.e. the model giving the smallest test set error) while keeping the tr...
Learning sequences of compatible actions among agents Polat, Faruk (2002-03-01) Action coordination in multiagent systems is a difficult task especially in dynamic environments. If the environment possesses cooperation, least communication, incompatibility and local information constraints, the task becomes even more difficult. Learning compatible action sequences to achieve a designated goal under these constraints is studied in this work. Two new multiagent learning algorithms called QACE and NoCommQACE are developed. To improve the performance of the QACE and NoCommQACE algorithms f...

Citation Formats

S. A. Özyeğin, “Towards Uncertainty-Aware Disentangled Representations,” M.S. - Master of Science, Middle East Technical University, 2021.