COFAR: Commonsense and Factual Reasoning in Image Search

TL;DR

This paper introduces KRAMT, a unified multimodal framework that enhances image search by integrating commonsense and factual knowledge, enabling reasoning beyond visual recognition, and demonstrates its effectiveness on the new COFAR dataset.

Contribution

The paper presents KRAMT, a novel knowledge retrieval-augmented multimodal transformer that incorporates encyclopedic knowledge into image search, addressing limitations of visual-only recognition.

Findings

KRAMT outperforms existing methods on the COFAR dataset.

The framework effectively grounds knowledge in visual content.

Enhanced reasoning improves search accuracy for complex queries.

Abstract

One characteristic that makes humans superior to modern artificially intelligent models is the ability to interpret images beyond what is visually apparent. Consider the following two natural language search queries - (i) "a queue of customers patiently waiting to buy ice cream" and (ii) "a queue of tourists going to see a famous Mughal architecture in India." Interpreting these queries requires one to reason with (i) Commonsense such as interpreting people as customers or tourists, actions as waiting to buy or going to see; and (ii) Fact or world knowledge associated with named visual entities, for example, whether the store in the image sells ice cream or whether the landmark in the image is a Mughal architecture located in India. Such reasoning goes beyond just visual recognition. To enable both commonsense and factual reasoning in the image search, we present a unified framework, namely Knowledge Retrieval-Augmented Multimodal Transformer (KRAMT), that treats the named visual entities in an image as a gateway to encyclopedic knowledge and leverages them along with natural language query to ground relevant knowledge. Further, KRAMT seamlessly integrates visual content and grounded knowledge to learn alignment between images and search queries. This unified framework is then used to perform image search requiring commonsense and factual reasoning. The retrieval performance of KRAMT is evaluated and compared with related approaches on a new dataset we introduce - namely COFAR. We make our code and dataset available at https://vl2g.github.io/projects/cofar