You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval

TL;DR

This paper introduces a novel duet framework combining sketches and text for fine-grained image retrieval, enhancing precision and enabling new applications by leveraging pre-trained CLIP models without extensive textual descriptions.

Contribution

It proposes a compositionality framework that integrates sketches and text for fine-grained retrieval, extending capabilities beyond sketch-only methods using pre-trained CLIP models.

Findings

Enhanced retrieval precision with combined sketch and text inputs

Enabled fine-grained queries incorporating color and context

Extended to applications like image retrieval and attribute transfer

Abstract

Two primary input modalities prevail in image retrieval: sketch and text. While text is widely used for inter-category retrieval tasks, sketches have been established as the sole preferred modality for fine-grained image retrieval due to their ability to capture intricate visual details. In this paper, we question the reliance on sketches alone for fine-grained image retrieval by simultaneously exploring the fine-grained representation capabilities of both sketch and text, orchestrating a duet between the two. The end result enables precise retrievals previously unattainable, allowing users to pose ever-finer queries and incorporate attributes like colour and contextual cues from text. For this purpose, we introduce a novel compositionality framework, effectively combining sketches and text using pre-trained CLIP models, while eliminating the need for extensive fine-grained textual descriptions. Last but not least, our system extends to novel applications in composed image retrieval, domain attribute transfer, and fine-grained generation, providing solutions for various real-world scenarios.