Large-Scale Unsupervised Object Discovery
share
Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations which 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. Extensive experiments with COCO and OpenImages demonstrate 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 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 average precision (AP) than all other methods for datasets ranging from 20K to 1.7M images.
READ FULL TEXT