DeepAI AI Chat
Log In Sign Up

CBIR using Pre-Trained Neural Networks

by   Agnel Lazar Alappat, et al.

Much of the recent research work in image retrieval, has been focused around using Neural Networks as the core component. Many of the papers in other domain have shown that training multiple models, and then combining their outcomes, provide good results. This is since, a single Neural Network model, may not extract sufficient information from the input. In this paper, we aim to follow a different approach. Instead of the using a single model, we use a pretrained Inception V3 model, and extract activation of its last fully connected layer, which forms a low dimensional representation of the image. This feature matrix, is then divided into branches and separate feature extraction is done for each branch, to obtain multiple features flattened into a vector. Such individual vectors are then combined, to get a single combined feature. We make use of CUB200-2011 Dataset, which comprises of 200 birds classes to train the model on. We achieved a training accuracy of 99.46 for the same. On further use of 3 branched global descriptors, we improve the validation accuracy to 88.89 extraction method.


Research on Dual Channel News Headline Classification Based on ERNIE Pre-training Model

The classification of news headlines is an important direction in the fi...

Co-occurrence of deep convolutional features for image search

Image search can be tackled using deep features from pre-trained Convolu...

Speech-Image Semantic Alignment Does Not Depend on Any Prior Classification Tasks

Semantically-aligned (speech, image) datasets can be used to explore "vi...

Transformaly – Two (Feature Spaces) Are Better Than One

Anomaly detection is a well-established research area that seeks to iden...

Homogeneous Vector Capsules Enable Adaptive Gradient Descent in Convolutional Neural Networks

Capsules are the name given by Geoffrey Hinton to vector-valued neurons....

Topological Gradient-based Competitive Learning

Topological learning is a wide research area aiming at uncovering the mu...