Deep Metric Learning With Alternating Projections Onto Feasible Sets

Download

index.pdf

Date

2021-01-01

Author

Can, Oğul
Gürbüz, Yeti Z.
Alatan, Abdullah Aydın

Metadata

Show full item record

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

Item Usage Stats

142
views

48
downloads

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 constraints only for particular samples (a sample from each class) of the training data. Then, the feasible point problem is to be approximately solved by performing alternating projections onto those feasible sets. Such an approach introduces a regularization term and results in minimizing a typical loss function with a systematic batch set construction where these batches are constrained to contain the same sample from each class for a certain number of iterations. The proposed technique is applied with the well-accepted losses and evaluated on three popular benchmark datasets for image retrieval and clustering. Outperforming state-of-the-art, the proposed approach consistently improves the performance of the integrated loss functions with no additional computational cost.

Subject Keywords

Metric learning, projections, Metric learning, Projections

URI

https://hdl.handle.net/11511/99611

DOI

https://doi.org/10.1109/icip42928.2021.9506317

Conference Name

2021 IEEE International Conference on Image Processing, ICIP 2021

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Deep metric learning with distance sensitive entangled triplet losses Karaman, Kaan; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2021-2-12) 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 t...
A Comparative Study on Distance Metrics in Self- Supervised Unstructured Road Detection Domain Özütemiz, Kadri Buğra; Hacınecipoğlu, Akif; Koku, Ahmet Buğra; Konukseven, Erhan İlhan (2013-09-20) In pattern recognition/machine learning domain, selecting appropriate distance metric for the problem to find the distance between feature vectors or the distance between a feature vector and decision boundary is important in order to have satisfying results from the algorithm designed. In this study, in order to find the most appropriate distance metric to use in classification of road/non-road regions in streaming images, 6 different distance metrics are implemented and their classification performances a...
Novel Optimization Models to Generalize Deep Metric Learning Gürbüz, Yeti Ziya; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2022-8-24) Deep metric learning (DML) aims to fit a parametric embedding function to data of semantic information (e.g. images) so that l2-distance between embedded samples is low whenever they share similar semantic entities. An embedding function of such behavior is attained by minimizing empirical expected pairwise loss that penalizes inter-/intra-class proximity violations in embedding space. Proxy-based methods which use a learnable embedding vector per class in their loss formulation are state-of-the-art. We fir...
A Bayesian Approach to Learning Scoring Systems Ertekin Bolelli, Şeyda (2015-12-01) We present a Bayesian method for building scoring systems, which are linear models with coefficients that have very few significant digits. Usually the construction of scoring systems involve manual efforthumans invent the full scoring system without using data, or they choose how logistic regression coefficients should be scaled and rounded to produce a scoring system. These kinds of heuristics lead to suboptimal solutions. Our approach is different in that humans need only specify the prior over what the ...
Discrete tomographic reconstruction methods from the theories of optimization and inverse problems : application in VLSI microchip production Özgür, Osman; Weber, Gerhard Wilhelm; Department of Scientific Computing (2006) Optimization theory is a key technology for inverse problems of reconstruction in science, engineering and economy. Discrete tomography is a modern research field dealing with the reconstruction of finite objects in, e.g., VLSI chip design, where this thesis will focus on. In this work, a framework with its supplementary algorithms and a new problem reformulation are introduced to approximately resolve this NP-hard problem. The framework is modular, so that other reconstruction methods, optimization techniq...

Citation Formats

O. Can, Y. Z. Gürbüz, and A. A. Alatan, “Deep Metric Learning With Alternating Projections Onto Feasible Sets,” Alaska, Amerika Birleşik Devletleri, 2021, vol. 2021-September, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/99611.