Deep Features For CBIR With Scarce Data Using Hebbian Learning

Abstract

Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). In recent work, biologically inspired \textit\{Hebbian\} learning algorithms have shown promises for DNN training. In this contribution, we study the performance of such algorithms in the development of feature extractors for CBIR tasks. Specifically, we consider a semi-supervised learning strategy in two steps: first, an unsupervised pre-training stage is performed using Hebbian learning on the image dataset; second, the network is fine-tuned using supervised Stochastic Gradient Descent (SGD) training. For the unsupervised pre-training stage, we explore the nonlinear Hebbian Principal Component Analysis (HPCA) learning rule. For the supervised fine-tuning stage, we assume sample efficiency scenarios, in which the amount of labeled samples is just a small fraction of the whole dataset. Our experimental analysis, conducted on the CIFAR10 and CIFAR1

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keylagani2022deep

Related papers

• Detailed Investigation Of Deep Features With Sparse Representation And Dimensionality Reduction In CBIR: A Comparative Study (2018)11.29
• CBIR Using Features Derived By Deep Learning (2020)12.02
• Leveraging High-resolution Features For Improved Deep Hashing-based Image Retrieval (2024)4.52
• Sketches Image Analysis: Web Image Search Engine Usinglsh Index And DNN Inceptionv3 (2021)0.00
• Deep Learning Approaches For Image Retrieval And Pattern Spotting In Ancient Documents (2019)0.00
• Efficient Feature Embedding Of 3D Brain MRI Images For Content-based Image Retrieval With Deep Metric Learning (2019)8.35
• Medical Image Retrieval Using Deep Convolutional Neural Network (2017)19.35
• Deep Learning For Image Search And Retrieval In Large Remote Sensing Archives (2020)10.74