Embedding Arithmetic of Multimodal Queries for Image Retrieval

Guillaume Couairon, Matthijs Douze, Matthieu Cord, Holger Schwenk; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 4950-4958


Latent text representations exhibit geometric regularities, such as the famous analogy: queen is to king what woman is to man. Such structured semantic relations were not demonstrated on image representations. Recent works aiming at bridging this semantic gap embed images and text into a multimodal space, enabling the transfer of text-defined transformations to the image modality. We introduce the SIMAT dataset to evaluate the task of Image Retrieval with Multimodal queries. SIMAT contains 6k images and 18k textual transformation queries that aim at either replacing scene elements or changing pairwise relationships between scene elements. The goal is to retrieve an image consistent with the (source image, text transformation) query. We use an image/text matching oracle (OSCAR) to assess whether the image transformation is successful. The SIMAT dataset will be publicly available. We use SIMAT to evaluate the geometric properties of multimodal embedding spaces trained with an image/text matching objective, like CLIP. We show that vanilla CLIP embeddings are not very well suited to transform images with delta vectors, but that a simple finetuning on the COCO dataset can bring dramatic improvements. We also study whether it is beneficial to leverage pretrained universal sentence encoders (FastText, LASER and LaBSE).

Related Material

@InProceedings{Couairon_2022_CVPR, author = {Couairon, Guillaume and Douze, Matthijs and Cord, Matthieu and Schwenk, Holger}, title = {Embedding Arithmetic of Multimodal Queries for Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4950-4958} }