Large-Scale Unsupervised Object Discovery - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Large-Scale Unsupervised Object Discovery

Résumé

Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulation of UOD as a ranking problem, amenable to the arsenal of distributed methods available for eigenvalue problems and link analysis. Through the use of self-supervised features, we also demonstrate the first effective fully unsupervised pipeline for UOD. Extensive experiments on COCO and OpenImages show that, in the single-object discovery setting where a single prominent object is sought in each image, the proposed LOD (Large-scale Object Discovery) approach is on par with, or better than the state of the art for medium-scale datasets (up to 120K images), and over 37% better than the only other algorithms capable of scaling up to 1.7M images. In the multi-object discovery setting where multiple objects are sought in each image, the proposed LOD is over 14% better in average precision (AP) than all other methods for datasets ranging from 20K to 1.7M images. Using self-supervised features, we also show that the proposed method obtains state-of-the-art UOD performance on OpenImages. Our code is publicly available at https://github.com/huyvvo/LOD.

Dates et versions

hal-03541587 , version 1 (24-01-2022)

Identifiants

Citer

Huy V. Vo, Elena Sizikova, Cordelia Schmid, Patrick Pérez, Jean Ponce. Large-Scale Unsupervised Object Discovery. NeurIPS - Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Virtual, Canada. ⟨hal-03541587⟩
34 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More