Attention-Based Image Captioning Using DenseNet Features

Md. Zakir Hossain, Ferdous Sohel, Mohd Fairuz Shiratuddin, Hamid Laga, Mohammed Bennamoun

Abstract: We present an attention-based image captioning method using DenseNet features. Conventional image captioning methods depend on visual information of the whole scene to generate image captions. Such a mechanism often fails to get the information of salient objects and cannot generate semantically correct captions. We consider an attention mechanism that can focus on relevant parts of the image to generate fine-grained description of that image. We use image features from DenseNet. We conduct our experiments on the MSCOCO dataset. Our proposed method achieved 53.6, 39.8, and 29.5 on BLEU-2, 3, and 4 metrics, respectively, which are superior to the state-of-the-art methods.