KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models
This work addresses image ad understanding, which is broadly relevant to the advertising industry, but it is incremental as it adapts existing models rather than introducing a new paradigm.
The paper tackles the problem of image ad understanding by benchmarking pre-trained vision-language models and proposing a feature adaptation strategy to fuse multimodal information and incorporate real-world entity knowledge, achieving improved performance on this under-explored task.
Image ad understanding is a crucial task with wide real-world applications. Although highly challenging with the involvement of diverse atypical scenes, real-world entities, and reasoning over scene-texts, how to interpret image ads is relatively under-explored, especially in the era of foundational vision-language models (VLMs) featuring impressive generalizability and adaptability. In this paper, we perform the first empirical study of image ad understanding through the lens of pre-trained VLMs. We benchmark and reveal practical challenges in adapting these VLMs to image ad understanding. We propose a simple feature adaptation strategy to effectively fuse multimodal information for image ads and further empower it with knowledge of real-world entities. We hope our study draws more attention to image ad understanding which is broadly relevant to the advertising industry.