Image Difference Captioning with Pre-training and Contrastive Learning
This work addresses the problem of generating natural language descriptions for visual differences between similar images, which is incremental as it builds on existing pre-training paradigms.
The paper tackles the Image Difference Captioning task by proposing a pre-training and contrastive learning framework to address fine-grained visual differences and limited supervised data, achieving effectiveness on benchmark datasets like CLEVR-Change and Birds-to-Words.
The Image Difference Captioning (IDC) task aims to describe the visual differences between two similar images with natural language. The major challenges of this task lie in two aspects: 1) fine-grained visual differences that require learning stronger vision and language association and 2) high-cost of manual annotations that leads to limited supervised data. To address these challenges, we propose a new modeling framework following the pre-training-finetuning paradigm. Specifically, we design three self-supervised tasks and contrastive learning strategies to align visual differences and text descriptions at a fine-grained level. Moreover, we propose a data expansion strategy to utilize extra cross-task supervision information, such as data for fine-grained image classification, to alleviate the limitation of available supervised IDC data. Extensive experiments on two IDC benchmark datasets, CLEVR-Change and Birds-to-Words, demonstrate the effectiveness of the proposed modeling framework. The codes and models will be released at https://github.com/yaolinli/IDC.