Retrieval Augmentation for Deep Neural Networks

TL;DR

This paper introduces a retrieval augmentation method that leverages nearest training examples to improve deep neural network predictions during training and testing, demonstrating effectiveness in image captioning and sentiment analysis tasks.

Contribution

It proposes a novel retrieval-based augmentation technique that uses nearest training examples to enhance neural network performance during both training and inference.

Findings

Improved accuracy in image captioning on Flickr8 dataset.

Enhanced sentiment analysis results on IMDB dataset.

Code implementation is publicly available for reproducibility.

Abstract

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining examples for the current prediction. In this work, we actively exploit the training data, using the information from nearest training examples to aid the prediction both during training and testing. Specifically, our approach uses the target of the most similar training example to initialize the memory state of an LSTM model, or to guide attention mechanisms. We apply this approach to image captioning and sentiment analysis, respectively through image and text retrieval. Results confirm the effectiveness of the proposed approach for the two tasks, on the widely used Flickr8 and IMDB datasets. Our code is publicly available at http://github.com/RitaRamo/retrieval-augmentation-nn.