Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network

TL;DR

This paper introduces a novel transformer-based encoder-decoder model with a ResNet-101 image encoder for Bangla image captioning, achieving state-of-the-art results on the BanglaLekhaImageCaptions dataset.

Contribution

It presents a new architecture combining CNN and transformer models for improved Bangla image captioning performance.

Findings

Outperforms existing Bengali captioning models

Achieves new benchmark scores on BLEU and METEOR metrics

Captures fine-grained image details in captions

Abstract

Automatic Image Captioning is the never-ending effort of creating syntactically and validating the accuracy of textual descriptions of an image in natural language with context. The encoder-decoder structure used throughout existing Bengali Image Captioning (BIC) research utilized abstract image feature vectors as the encoder's input. We propose a novel transformer-based architecture with an attention mechanism with a pre-trained ResNet-101 model image encoder for feature extraction from images. Experiments demonstrate that the language decoder in our technique captures fine-grained information in the caption and, then paired with image features, produces accurate and diverse captions on the BanglaLekhaImageCaptions dataset. Our approach outperforms all existing Bengali Image Captioning work and sets a new benchmark by scoring 0.694 on BLEU-1, 0.630 on BLEU-2, 0.582 on BLEU-3, and 0.337 on METEOR.