Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection
Authors:
- Parthipan SivaPSParthipan Siva
- Chris RussellCRChris Russell
- Tao XiangTXTao Xiang
- Lourdes AgapitoLALourdes Agapito
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3238-3245
Abstract
We propose a principled probabilistic formulation of object saliency as a sampling problem. This novel formulation allows us to learn, from a large corpus of unlabelled images, which patches of an image are of the greatest interest and most likely to correspond to an object. We then sample the object saliency map to propose object locations. We show that using only a single object location proposal per image, we are able to correctly select an object in over 42% of the images in the Pascal VOC 2007 dataset, substantially outperforming existing approaches. Furthermore, we show that our object proposal can be used as a simple unsupervised approach to the weakly supervised annotation problem. Our simple unsupervised approach to annotating objects of interest in images achieves a higher annotation accuracy than most weakly supervised approaches.Keywords
This publication has 26 references indexed in Scilit:
- Scene recognition and weakly supervised object localization with deformable part-based models2011
- Saliency Density Maximization for Efficient Visual Objects DiscoveryIEEE Transactions on Circuits and Systems for Video Technology, 2011
- A framework for visual saliency detection with applications to image thumbnailing2009
- Weakly supervised discriminative localization and classification: a joint learning process2009
- Scene completion using millions of photographs2007
- Saliency Detection: A Spectral Residual Approach2007
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- Object recognition from local scale-invariant features1999
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998