0% Complete
Home
/
14th International Conference on Computer and Knowledge Engineering
Cluster Sampling: A Cluster-Driven Sampling Strategy for Deep Metric Learning
Authors :
Hamideh Rafiee
1
Ahmad Ali Abin
2
Seyed Soroush Majd
3
1- Computer Science and Engineering Department, Shahid Beheshti University, Tehran, Iran
2- Computer Science and Engineering Department, Shahid Beheshti University, Tehran, Iran
3- Computer Science and Engineering Department Shahid Beheshti University
Keywords :
Deep Learning،Metric Learning،Deep Metric Learning،Sampling،Clustering
Abstract :
Abstract—Deep metric learning has gained significant attention recently due to its promising performance in image retrieval, face recognition, and clustering tasks. Deep metric learning algorithms map the original data from the initial feature space to a new embedded space by learning a mapping function, where the discriminative power of the samples is increased. Sampling strategies are a critical aspect of deep metric learning algorithms, as they determine the choice of training samples that shape the network’s learning process. This research introduces a novel sampling approach designed to optimize this selection for improved model performance. Given the high dimensionality of embedded spaces, choosing a sampling strategy is critical for enhancing the quality of learned representations and improving model performance. However, existing sampling methods often face significant challenges, such as slow convergence and the tendency to get trapped in suboptimal local minima. To address these challenges, this research proposes a novel sampling approach that leverages the clustering of sample representations within training batches to identify and select the most informative samples for effective training. This approach ensures a more dynamic learning process by clustering data based on shared features and selecting samples both within clusters and between related clusters. The selected samples enable the model to better learn the underlying data structure, thereby enhancing the discriminative power and robustness of the learned metrics. The effectiveness of the proposed approach is validated through empirical evaluations on the cars196 dataset, where it outperforms existing sampling methods.
Papers List
List of archived papers
An intelligent linguistic error detection approach to automated diagnosis of Dyslexia disorder in Persian speaking children
Fatemeh Asghari - Mahsa Khorasani - Mohsen Kahani - Seyed Amir Amin Yazdi - Mahdi Arkhodi Ghalenoei
Deep Learning-Driven Beamforming Optimization for High-Performance 5G Planar Antenna Arrays
Rahman Mohammadi - Seyed Reza Razavi Pour
Reversible Data Insertion in Encryption Domain Based on Reduced Quad Difference Expansion
Alireza Ghaemi - Mohammad Zare Ehteshami - Amirhossein Ghaemi
Non-Negative Matrix Factorization improves Residual Neural Networks
Hojjat Moayed
Density Estimation Helps Adversarial Robustness
Afsaneh Hasanebrahimi - Bahareh Kaviani Baghbaderani - Reshad Hosseini - Ahmad Kalhor
PeQa: a Massive Persian Quenstion-Answering and Chatbot Dataset
Fatemeh Zahra Arshia - Mohammad Ali Keyvanrad - Saeedeh Sadat Sadidpour - Sayyid Mohammad Reza Mohammadi
Forecasting El Niño Six Months in Advance Utilizing Augmented Convolutional Neural Network
Mohammad Naisipour - Iraj Saeedpanah - Arash Adib - Mohammad Hossein Neisi Pour
Overview of Electric Vehicles Charging Stations in Smart Grids
Mohammed Wadi - Wisam Elmasry - Mohammed Jouda - Hossein Shahinzadeh - Gevork B. Gharehpetian
Divide and Conquer Approach to Long Genomic Sequence Alignment
Mahmoud Naghibzadeh - Samira Babaei - Behshid Behkmal - Mojtaba Hatami
A New Hypercube Variant: Pruned Shuffle Connected Cube
Reza Latifi - Mahmoud Naghibzadeh
more
Samin Hamayesh - Version 41.7.6