Channel and spatial attention mechanism for fashion image captioning

Abstract

Image captioning aims to automatically generate one or more description sentences for a given input image. Most of the existing captioning methods use encoder-decoder model which mainly focus on recognizing and capturing the relationship between objects appearing in the input image. However, when generating captions for fashion images, it is important to not only describe the items and their relationships, but also mention attribute features of clothes (shape, texture, style, fabric, and more). In this study, one novel model is proposed for fashion image captioning task which can capture not only the items and their relationship, but also their attribute features. Two different attention mechanisms (spatial-attention and channel-wise attention) is incorporated to the traditional encoder-decoder model, which dynamically interprets the caption sentence in multi-layer feature map in addition to the depth dimension of the feature map. We evaluate our proposed architecture on Fashion-Gen using three different metrics (CIDEr, ROUGE-L, and BLEU-1), and achieve the scores of 89.7, 50.6 and 45.6, respectively. Based on experiments, our proposed method shows significant performance improvement for the task of fashion-image captioning, and outperforms other state-of-the-art image captioning methods.