Multi-instance Methods for Partially Supervised Image Segmentation

@inproceedings{Mller2011MultiinstanceMF,
  title={Multi-instance Methods for Partially Supervised Image Segmentation},
  author={Andreas C. M{\"u}ller and Sven Behnke},
  booktitle={PSL},
  year={2011}
}
In this paper, we propose a new partially supervised multi-class image segmentation algorithm. We focus on the multi-class, single-label setup, where each image is assigned one of multiple classes. We formulate the problem of image segmentation as a multi-instance task on a given set of overlapping candidate segments. Using these candidate segments, we solve the multi-instance, multi-class problem using multi-instance kernels with an SVM. This computationally advantageous approach, which… 

Augmented Multiple Instance Regression for Inferring Object Contours in Bounding Boxes

TLDR
An approach is proposed that formulates the task of hypothesis selection as the problem of multiple instance regression (MIR), and augments information derived from the object contours to guide and regularize the training process of MIR.

Learning From Weakly Supervised Data by The Expectation Loss SVM (e-SVM) algorithm

TLDR
This work proposes a novel learning algorithm called expectation loss SVM (e-SVM) that is devoted to the problems where only the "positiveness" instead of a binary label of each training sample is available, and achieves the state-of-the-art object detection performance on PASCAL VOC 2007 dataset.

Multiple instance learning under real-world conditions

TLDR
This thesis proposes a method for bag classification which relies on the identification of positive instances to train an ensemble of instance classifiers and proposes a bag classification method that learns under these conditions.

A Bibliography of Papers in Lecture Notes in Computer Science (2012): Volumes 6121{7125

(∆ + 1) [1577]. (ρ,G) [266]. (r|p) [781]. 1 [1022]. 1 [1342]. 2 [27, 1294, 1138, 432, 1028, 281, 758, 272, 1440, 546, 861, 867, 1352, 578, 561]. 3 [579, 1293, 1381, 176, 1355, 1623, 1294, 1012, 1358,

On classification with bags, groups and sets

References

SHOWING 1-10 OF 38 REFERENCES

Joint multi-label multi-instance learning for image classification

TLDR
This work proposes an integrated multi- label multi-instance learning (MLMIL) approach based on hidden conditional random fields (HCRFs), which simultaneously captures both the connections between semantic labels and regions, and the correlations among the labels in a single formulation.

Weakly supervised semantic segmentation with a multi-image model

TLDR
A novel method for weakly supervised semantic segmentation using a multi-image model (MIM) - a graphical model for recovering the pixel labels of the training images and introducing an “objectness” potential, that helps separating objects from background classes.

A Convex Method for Locating Regions of Interest with Multi-instance Learning

TLDR
Two convex optimization methods which maximize the margin of concepts via key instance generation at the instance-level and bag-level, respectively are proposed which can effectively locate ROIs and achieve performances competitive with state-of-the-art algorithms on benchmark data sets.

A New SVM Approach to Multi-instance Multi-label Learning

  • Nam Nguyen
  • Computer Science
    2010 IEEE International Conference on Data Mining
  • 2010
TLDR
This paper addresses the problem of multi-instance multi-label learning (MIML) where each example is associated with not only multiple instances but also multiple class labels and presents an efficient method combining the stochastic gradient decent and alternating optimization approaches to solve the QP and IP optimizations.

ClassCut for Unsupervised Class Segmentation

We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object instances and learning a class model. The method is based on a segmentation

Class segmentation and object localization with superpixel neighborhoods

TLDR
A method to identify and localize object classes in images by constructing a classifier on the histogram of local features found in each superpixel using superpixels as the basic unit of a class segmentation or pixel localization scheme.

Associative hierarchical CRFs for object class image segmentation

TLDR
This work proposes a hierarchical random field model, that allows integration of features computed at different levels of the quantisation hierarchy, and evaluates its efficiency on some of the most challenging data-sets for object class segmentation, and shows it obtains state-of-the-art results.

Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning

  • A. VezhnevetsJ. Buhmann
  • Computer Science
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
TLDR
An external task of geometric context estimation is used to improve on the task of semantic segmentation, using Semantic Texton Forest (STF) as the basic framework and extending it for the MIL setting.

M3MIML: A Maximum Margin Method for Multi-instance Multi-label Learning

TLDR
A maximum margin method is proposed for MIML which directly exploits the connections between instances and labels and achieves superior performance over existing M IML methods.

Efficient scale space auto-context for image segmentation and labeling

  • Jiayan JiangZ. Tu
  • Computer Science
    2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
TLDR
Combining DAOC, the scale-space approach, and the region-based voting scheme for autocontext, the overall algorithm is significantly faster than the original auto-context, with improved accuracy over many of the existing algorithms on theMSRC and VOC 2007 datasets.