Exploring CLIP for Real World, Text-based Image Retrieval
Manal Sultan, Lia Jacobs, Abby Stylianou, Robert B. Pless · 2023
We consider the ability of CLIP features to support text-driven image retrieval. Traditional image-based queries sometimes misalign with user intentions due to their focus on irrelevant image components. To overcome this, we explore the potential of text-based image retrieval, specifically using Contrastive Language-Image Pretraining (CLIP) models. CLIP models, trained on large datasets of image-caption pairs, offer a promising approach by allowing natural language descriptions for more targeted queries. We explore the effectiveness of text-driven image retrieval based on CLIP features by evaluating the image similarity for progressively more detailed queries. We find that there is a sweet-spot of detail in the text that gives best results and find that words describing the "tone" of a scene (such as messy, dingy) are quite important in maximizing text-image similarity.