SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning

TL;DR

This paper introduces SD-RSIC, a novel remote sensing image captioning method that summarizes training captions to reduce redundancy and adaptively combines them with standard captions, improving captioning performance.

Contribution

The paper proposes a new summarization and adaptive weighting strategy for RS image captioning, addressing redundancy in training captions and enhancing model effectiveness.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively reduces redundancy in training captions

Improves captioning accuracy and semantic relevance

Abstract

Deep neural networks (DNNs) have been recently found popular for image captioning problems in remote sensing (RS). Existing DNN based approaches rely on the availability of a training set made up of a high number of RS images with their captions. However, captions of training images may contain redundant information (they can be repetitive or semantically similar to each other), resulting in information deficiency while learning a mapping from the image domain to the language domain. To overcome this limitation, in this paper, we present a novel Summarization Driven Remote Sensing Image Captioning (SD-RSIC) approach. The proposed approach consists of three main steps. The first step obtains the standard image captions by jointly exploiting convolutional neural networks (CNNs) with long short-term memory (LSTM) networks. The second step, unlike the existing RS image captioning methods, summarizes the ground-truth captions of each training image into a single caption by exploiting sequence to sequence neural networks and eliminates the redundancy present in the training set. The third step automatically defines the adaptive weights associated to each RS image to combine the standard captions with the summarized captions based on the semantic content of the image. This is achieved by a novel adaptive weighting strategy defined in the context of LSTM networks. Experimental results obtained on the RSCID, UCM-Captions and Sydney-Captions datasets show the effectiveness of the proposed approach compared to the state-of-the-art RS image captioning approaches. The code of the proposed approach is publicly available at https://gitlab.tubit.tu-berlin.de/rsim/SD-RSIC.