Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee
This addresses a fine-grained visual understanding challenge for computer vision and natural language processing, though it is incremental as it builds on existing captioning approaches.
The paper tackles the problem of generating natural language descriptions of differences between image pairs, introducing a new dataset and an encoder-decoder framework with feature fusing techniques and a discriminating referee. It outperforms state-of-the-art methods by a large margin on two datasets.
In this paper, we investigate a novel problem of telling the difference between image pairs in natural language. Compared to previous approaches for single image captioning, it is challenging to fetch linguistic representation from two independent visual information. To this end, we have proposed an effective encoder-decoder caption framework based on Hyper Convolution Net. In addition, a series of novel feature fusing techniques for pairwise visual information fusing are introduced and a discriminating referee is proposed to evaluate the pipeline. Because of the lack of appropriate datasets to support this task, we have collected and annotated a large new dataset with Amazon Mechanical Turk (AMT) for generating captions in a pairwise manner (with 14764 images and 26710 image pairs in total). The dataset is the first one on the relative difference caption task that provides descriptions in free language. We evaluate the effectiveness of our model on two datasets in the field and it outperforms the state-of-the-art approach by a large margin.