CLIP4IDC: CLIP for Image Difference Captioning
This addresses a domain-specific challenge in image difference captioning for applications like visual question answering or image editing, but it is incremental as it builds on existing CLIP technology.
The paper tackles the problem of generating captions for differences between similar images by adapting CLIP's visual encoder to better capture and align image pair differences based on textual descriptions, achieving state-of-the-art results on three benchmark datasets.
Image Difference Captioning (IDC) aims at generating sentences to describe differences between two similar-looking images. Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor. Accordingly, two major issues may arise: (1) a large domain gap usually exists between the pre-training datasets used for training such a visual encoder and that of the downstream IDC task, and (2) the visual feature extractor, when separately encoding two images, often does not effectively encode the visual changes between two images. Due to the excellent zero-shot performance of the recently proposed CLIP, we thus propose CLIP4IDC to transfer a CLIP model for the IDC task to address those issues. Different from directly fine-tuning CLIP to generate sentences, we introduce an adaptation training process to adapt CLIP's visual encoder to capture and align differences in image pairs based on the textual descriptions. Experiments on three IDC benchmark datasets, CLEVR-Change, Spot-the-Diff, and Image-Editing-Request, demonstrate the effectiveness of CLIP4IDC.