CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
This work addresses the problem of improving generalizability and versatility in composed image retrieval for applications in AI and computer vision, representing a significant advance with novel methods and a large dataset.
The paper tackles the problem of zero-shot composed image retrieval (ZS-CIR) by proposing CompoDiff, a diffusion-based model, and introduces SynthTriplets18M, a synthetic dataset with 18.8 million triplets, to address limitations in dataset scale and condition types. It achieves state-of-the-art results on four benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, and enables versatile retrieval with conditions like negative text and image masks.
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