DeepHashing using TripletLoss

TL;DR

This paper introduces improved training techniques for Deep Hashing models using triplet loss, achieving faster training and a 5% accuracy boost over previous methods, with potential for further performance gains.

Contribution

It proposes novel training techniques for Deep Hashing with triplet loss, enhancing efficiency and accuracy beyond prior models like Wang et al. (2016).

Findings

Achieved a 5% improvement in model performance.

Developed techniques for faster and more efficient training.

Potential for further improvements with larger models and data.

Abstract

Hashing is one of the most efficient techniques for approximate nearest neighbour search for large scale image retrieval. Most of the techniques are based on hand-engineered features and do not give optimal results all the time. Deep Convolutional Neural Networks have proven to generate very effective representation of images that are used for various computer vision tasks and inspired by this there have been several Deep Hashing models like Wang et al. (2016) have been proposed. These models train on the triplet loss function which can be used to train models with superior representation capabilities. Taking the latest advancements in training using the triplet loss I propose new techniques that help the Deep Hash-ing models train more faster and efficiently. Experiment result1show that using the more efficient techniques for training on the triplet loss, we have obtained a 5%percent improvement in our model compared to the original work of Wang et al.(2016). Using a larger model and more training data we can drastically improve the performance using the techniques we propose