CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gu, Geonmo, Chun, Sanghyuk, Kim, Wonjae, Jun, HeeJae, Kang, Yoohoon, Yun, Sangdoo
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916324874125312
author Gu, Geonmo
Chun, Sanghyuk
Kim, Wonjae
Jun, HeeJae
Kang, Yoohoon
Yun, Sangdoo
author_facet Gu, Geonmo
Chun, Sanghyuk
Kim, Wonjae
Jun, HeeJae
Kang, Yoohoon
Yun, Sangdoo
contents This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, but also enables a more versatile and controllable CIR by accepting various conditions, such as negative text, and image mask conditions. CompoDiff also shows the controllability of the condition strength between text and image queries and the trade-off between inference speed and performance, which are unavailable with existing CIR methods. The code and dataset are available at https://github.com/navervision/CompoDiff
format Preprint
id arxiv_https___arxiv_org_abs_2303_11916
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Gu, Geonmo
Chun, Sanghyuk
Kim, Wonjae
Jun, HeeJae
Kang, Yoohoon
Yun, Sangdoo
Computer Vision and Pattern Recognition
Information Retrieval
This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, but also enables a more versatile and controllable CIR by accepting various conditions, such as negative text, and image mask conditions. CompoDiff also shows the controllability of the condition strength between text and image queries and the trade-off between inference speed and performance, which are unavailable with existing CIR methods. The code and dataset are available at https://github.com/navervision/CompoDiff
title CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
topic Computer Vision and Pattern Recognition
Information Retrieval
url https://arxiv.org/abs/2303.11916