Deep metric learning with distance sensitive entangled triplet losses

Download

12626292.pdf

Date

2021-2-12

Author

Karaman, Kaan

Metadata

Show full item record

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

Item Usage Stats

525
views

236
downloads

Metric learning aims to define a distance that is able to measure the semantic difference between the instances in a dataset. The most recent approaches in this area mostly utilize deep neural networks as their models to map the input data into a feature space by finding appropriate distance metrics between the features. A number of loss functions are already defined in the literature based on these similarity metrics to discriminate instances in the feature space. In this thesis, we particularly focus on triplet loss functions in order to designate their gradients. It is argued that the gradients of the vanilla triplet loss function do not force the instances in a triplet along the right direction with the right magnitude. Hence, the similarities between the instances in a triplet and the natural phenomena of a free electrostatic charge being affected by several forces due to the other charged bodies located in certain coordinates in the space are exploited to determine the right direction and magnitude. Considering the partial gradients of the loss function with respect to the anchor, positive and negative instances of any valid triplet generated from the dataset, four novel triplet loss functions are proposed that cope with the problem pointed out. It is shown that these loss gradients gradually solve the drawbacks of the vanilla loss function. The performance increment of these losses, especially the METU loss, over the other triplet losses is presented by the results of several fair experiments on a commonly used fine-grained dataset: CUB200-2011. The results of the proposed techniques are comparable with respect to the score values of the state-of-the-art methods in the deep metric learning topic.

Subject Keywords

Deep Learning, Metric Learning, Fine-grained Classification, Image Classification, Image Retrieval, Object Classification

URI

https://hdl.handle.net/11511/89584

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Deep Metric Learning With Alternating Projections Onto Feasible Sets Can, Oğul; Gürbüz, Yeti Z.; Alatan, Abdullah Aydın (2021-01-01) Minimizers of the typical distance metric learning loss functions can be considered as "feasible points" satisfying a set of constraints imposed by the training data. We reformulate distance metric learning problem as finding a feasible point of a constraint set where the embedding vectors of the training data satisfy desired intra-class and inter-class proximity. The feasible set induced by the constraint set is expressed as the intersection of the relaxed feasible sets which enforce the proximity constrai...
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...
Multisource region attention network for fine-grained object recognition in remote sensing imagery Sümbül, Gencer; Cinbiş, Ramazan Gökberk; Aksoy, Selim (Institute of Electrical and Electronics Engineers (IEEE), 2019-07) Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related subcategories. Multisource data analysis that aims to leverage the complementary spectral, spatial, and structural information embedded in different sources is a promising direction toward solving the fine-grained recognition problem that involves low between-class variance, small training set sizes for rare classes, and class imbalance. However, the common assumption of coregistered ...
Extended Target Tracking and Classification Using Neural Networks Tuncer, Barkın; Kumru, Murat; Özkan, Emre (2019-01-01) Extended target/object tracking (ETT) problem involves tracking objects which potentially generate multiple measurements at a single sensor scan. State-of-the-art ETT algorithms can efficiently exploit the available information in these measurements such that they can track the dynamic behaviour of objects and learn their shapes simultaneously. Once the shape estimate of an object is formed, it can naturally be utilized by high-level tasks such as classification of the object type. In this work, we propose ...
Fine-grained object recognition and zero-shot learning in multispectral imagery Sumbul, Gencer; Cinbiş, Ramazan Gökberk; AKSOY, SELİM (2018-05-05) We present a method for fine-grained object recognition problem, that aims to recognize the type of an object among a large number of sub-categories, and zero-shot learning scenario on multispectral images. In order to establish a relation between seen classes and new unseen classes, a compatibility function between image features extracted from a convolutional neural network and auxiliary information of classes is learnt. Knowledge transfer for unseen classes is carried out by maximizing this function. Per...

Citation Formats

K. Karaman, “Deep metric learning with distance sensitive entangled triplet losses,” M.S. - Master of Science, Middle East Technical University, 2021.