Segmentation Propagation in ImageNet

Daniel Kuettel, Matthieu Guillaumin, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

ImageNet is a large-scale hierarchical database of object classes. We propose to automatically populate it with pixelwise segmentations, by leveraging existing manual annotations in the form of class labels and bounding-boxes. The key idea is to recursively exploit images segmented so far to guide the segmentation of new images. At each stage this propagation process expands into the images which are easiest to segment at that point in time, e.g. by moving to the semantically most related classes to those segmented so far. The propagation of segmentation occurs both (a) at the image level, by transferring existing segmentations to estimate the probability of a pixel to be foreground, and (b) at the class level, by jointly segmenting images of the same class and by importing the appearance models of classes that are already segmented. Through an experiment on 577 classes and 500k images we show that our technique (i) annotates a wide range of classes with accurate segmentations; (ii) effectively exploits the hierarchical structure of ImageNet; (iii) scales efficiently; (iv) outperforms a baseline GrabCut [1] initialized on the image center, as well as our recent segmentation transfer technique [2] on which this paper is based. Moreover, our method also delivers state-of-the-art results on the recent iCoseg dataset for co-segmentation.
Original languageEnglish
Title of host publicationComputer Vision - ECCV 2012
Subtitle of host publication12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VII
EditorsAndrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, Cordelia Schmid
PublisherSpringer-Verlag GmbH
Number of pages15
ISBN (Electronic)978-3-642-33786-4
ISBN (Print)978-3-642-33785-7
Publication statusPublished - 2012

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin / Heidelberg
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Dive into the research topics of 'Segmentation Propagation in ImageNet'. Together they form a unique fingerprint.

Cite this