Proceedings Article10.1109/ICCV.2005.148
LOCUS: learning object classes with unsupervised segmentation
John Winn,Nebojsa Jojic +1 more
- 17 Oct 2005
- Vol. 1, pp 756-763
TL;DR: LOCUS (learning object classes with unsupervised segmentation) is introduced which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and pose, allowing for significant within-class variation.
read more
Abstract: We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (learning object classes with unsupervised segmentation) which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and pose. A key aspect of this model is that the object appearance is allowed to vary from image to image, allowing for significant within-class variation. By iteratively updating the belief in the object's position, size, segmentation and pose, LOCUS avoids making hard decisions about any of these quantities and so allows for each to be refined at any stage. We show that LOCUS successfully learns an object class model from unlabeled images, whilst also giving segmentation accuracies that rival existing supervised methods. Finally, we demonstrate simultaneous recognition and segmentation in novel images using the learned models for a number of object classes, as well as unsupervised object discovery and tracking in video.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Learning to detect unseen object classes by between-class attribute transfer
Christoph H. Lampert,Hannes Nickisch,Stefan Harmeling +2 more
- 20 Jun 2009
TL;DR: The experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes, and assembled a new large-scale dataset, “Animals with Attributes”, of over 30,000 animal images that match the 50 classes in Osherson's classic table of how strongly humans associate 85 semantic attributes with animal classes.
Attribute-Based Classification for Zero-Shot Visual Object Categorization
TL;DR: In this article, the authors introduce attribute-based classification, where objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object's color or shape.
2K
SIFT Flow: Dense Correspondence across Scenes and Its Applications
TL;DR: SIFT flow is proposed, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence.
1.9K
TextonBoost : joint appearance, shape and context modeling for multi-class object recognition and segmentation
Jamie Shotton,John Winn,Carsten Rother,Antonio Criminisi +3 more
- 07 May 2006
TL;DR: A new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently, is proposed, which is used for automatic visual recognition and semantic segmentation of photographs.
References
Active shape models—their training and application
TL;DR: This work describes a method for building models by learning patterns of variability from a training set of correctly annotated images that can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes).
8.4K
Fast approximate energy minimization via graph cuts
TL;DR: This work presents two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves that allow important cases of discontinuity preserving energies.
"GrabCut": interactive foreground extraction using iterated graph cuts
Carsten Rother,Vladimir Kolmogorov,Andrew Blake +2 more
- 01 Aug 2004
TL;DR: A more powerful, iterative version of the optimisation of the graph-cut approach is developed and the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result.
An introduction to variational methods for graphical models
TL;DR: This paper presents a tutorial introduction to the use of variational methods for inference and learning in graphical models (Bayesian networks and Markov random fields), and describes a general framework for generating variational transformations based on convex duality.
What energy functions can be minimized via graph cuts
Vladimir Kolmogorov,R. Zabin +1 more
- 01 Jan 2004
TL;DR: This work gives a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables.