Timezone: »

Large-Scale Unsupervised Object Discovery
Van Huy Vo · Elena Sizikova · Cordelia Schmid · Patrick Pérez · Jean Ponce

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @

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~\cite{Lin2014cocodataset} and OpenImages~\cite{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.

Author Information

Van Huy Vo (INRIA/Valeo.ai/ENS)
Elena Sizikova (NYU)
Cordelia Schmid (Inria / Google)
Patrick Pérez (Valeo.ai)
Jean Ponce (Inria)

More from the Same Authors