A method for quadruplet sample selection in deep feature learning Derin Öznitelik Öǧrenme için Dördüz Örnek Seçme Yöntemi

Date

2018-07-05

Author

Karaman, Kaan
Gundogdu, Erhan
Koc, Aykut
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

74
views

0
downloads

Recently, the deep learning based feature learning methodologies have been developed to recognize the objects in fine-grained detail. In order to increase the discriminativeness and robustness of the utilized features, this paper proposes a sample selection methodology for the quadruplet based feature learning. The feature space is manipulated by using the hierarchical structure of the training set. In the training process, the quadruplets are selected by considering the distances between the samples in the feature space in order to improve the effectiveness of the training. We have shown by the experiments that the proposed method improves the fine-grained recognition accuracy.

Subject Keywords

Deep distance metric learning, Learning embeddings, Fine-grained classification/detection

URI

https://hdl.handle.net/11511/38876

DOI

https://doi.org/10.1109/siu.2018.8404251

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

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...
An Approach to manage variability in object-oriented applications with feature models Bulut, Ender; Şener, Cevat; Department of Computer Engineering (2014) In this thesis, an approach to manage variability in object-oriented applications by using a feature modeling language and a simple source code generation technique has been designed and developed. This approach provides developing configurable object oriented applications in a practical way. That is, an application developed with our approach takes just a configuration file including user selections in a pre-defined domain as input and then automatically configure and manage itself with respect to these se...
IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES Kaya, Emre Can; Alatan, Abdullah Aydın (2018-10-10) A novel extension to proposal-based detection is proposed in order to learn convolutional context features for determining boundaries of objects better. Objects and their context are aimed to be learned through parallel convolutional stages. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over baseline, ...
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...
Analysis of Face Recognition Algorithms for Online and Automatic Annotation of Personal Videos Yılmaztürk, Mehmet; Ulusoy Parnas, İlkay; Çiçekli, Fehime Nihan (Springer, Dordrecht; 2010-05-08) Different from previous automatic but offline annotation systems, this paper studies automatic and online face annotation for personal videos/episodes of TV series considering Nearest Neighbourhood, LDA and SVM classification with Local Binary Patterns, Discrete Cosine Transform and Histogram of Oriented Gradients feature extraction methods in terms of their recognition accuracies and execution times. The best performing feature extraction method and the classifier pair is found out to be SVM classification...

Citation Formats

K. Karaman, E. Gundogdu, A. Koc, and A. A. Alatan, “A method for quadruplet sample selection in deep feature learning Derin Öznitelik Öǧrenme için Dördüz Örnek Seçme Yöntemi,” 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/38876.