We propose a novel unsupervised learning algorithm to extract the layout of an image by learning latent object-related aspects. Unlike traditional image segmentation algorithms th...
Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can...
Robert Fergus, Fei-Fei Li 0002, Pietro Perona, And...
In this paper, we develop a system to classify the outputs of image segmentation algorithms as perceptually relevant or perceptually irrelevant with respect to human perception. T...
This paper describes a two-stage system for the recognition of postage meter values. A feed-forward Neural Abstraction Pyramid is initialized in an unsupervised manner and trained...
Abstract. Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects from a single category, although objects from multiple...
Takahiro Okabe, Yuhi Kondo, Kris M. Kitani, Yoichi...