Combining image-level and object-level inference for weakly supervised object recognition. application to fisheries acoustics

Authors:
R. Lefort;R. Fablet;I. Karoui;J.-M. Boucher
Affiliations:
Ifremer, STH, Plouzane, France and Institut Telecom, Telecom Bretagne, Lab., STICC, Brest cedex, France and Université Européenne de Bretagne;Institut Telecom, Telecom Bretagne, Lab-STICC, Brest cedex, France and Université Européenne de Bretagne;Ifremer, STH, Plouzane, France and Institut Telecom, Telecom Bretagne, Lab-STICC, Brest cedex, France and Université Européenne de Bretagne;Institut Telecom, Telecom Bretagne, Lab-STICC, Brest cedex, France and Université Européenne de Bretagne
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 3
Cited 2

Generative versus Discriminative Methods for Object Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Weakly Supervised Top-down Image Segmentation

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Semi-Supervised Learning

Semi-Supervised Learning

Weakly supervised classification of objects in images using soft random forests

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Object recognition using proportion-based prior information: Application to fisheries acoustics

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses weakly supervised object recognition. We show how the combination of an image-level inference, in terms of image-level object class priors, can lead to better training of object recognition models. Stated within a probabilistic setting, the proposed approach is applied to fisheries acoustics and fish school recognition.