Multi-class cosegmentation

By Armand Joulin, Francis R. Bach, Jean Ponce. 2012

300 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, background): “This framework has shown promising results in weakly-supervised and unsupervised computer vision tasks [1, 4, 5, 6, 16, 17, 29, 31].”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, methodology): “In computer vision these methods have been successfully applied to co-segmentation [19].”
Weakly-Supervised Alignment of Video with Text (2015, methodology): “Contrary to standard clustering techniques, it uses a discriminative cost function [2, 16] and it has been used in image co-segmentation [20, 21], object colocalization [22], person identification in video [6, 36], and alignment of labels to videos [7].”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “The separate-class results are quantified in Table 1, and compared to those of state-of-theart cosegmentation [29, 25, 26] and colocalization [40, 51] methods.”
Semantic Object Selection (2014, methodology): “Cosegmentation methods [9, 8, 10, 19] operate on multiple input images and select in each image a common object.”
How to Evaluate Foreground Maps (2014, background): “The common measures for evaluating a binary map are PASCAL’s VOC (Visual Object Classes) segmentation measure (referred to henceforth as PASCAL) [3, 11, 14] and Fβ-measure [2, 4, 10, 17, 23].”
Learning Discriminative Part Detectors for Image Classification and Cosegmentation (2013, unknown): “Its multi-class extensions [17, 18] try to segment out multiple classes of objects from images.”
Learning from Video and Text via Large-Scale Discriminative Clustering (2017, background): “This framework has shown promising results in weakly supervised and unsupervised computer vision tasks [1, 4, 5, 6, 16, 17, 30, 32].”
Webly Supervised Semantic Segmentation (2017, methodology): “[41] 35.”
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection (2015, background): “However, they mainly have two-fold differences: 1) co-saliency detection only focuses on detecting the common salient objects while co-segmentation methods also tend to segment the similar but non-salient background regions [25, 26]; 2) co-segmentation usually needs semi- or interactivesupervision [”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “With the emergence of large-scale image databases, such as the ImageNet [33] and personal photo streams on Flickr, the cosegmentation methods [34], [35], [36], [37], [38], [39], [40], [41] which can extract recurring objects from a set of images, has attracted increasing attentions in these years.”
Object Discovery: Soft Attributed Graph Mining (2016, background): “Some pioneering studies, including those on object discovery [30] and co-segmentation [31], [32], [33], can be thought of as a kind of object-level visual mining.”
Weakly-Supervised Dual Clustering for Image Semantic Segmentation (2013, methodology): “Co-segmentation [7, 8, 16] means to simultaneously segment a common salient foreground object from a set of images which can be seen as a special case of our work.”
Weakly Supervised Segmentation with Maximum Bipartite Graph Matching (2020, background): “Many traditional works[23, 51] generate the foreground masks of the common objects by maximizing an energy function.”
CRNet: Cross-Reference Networks for Few-Shot Segmentation (2020, methodology): “Inspired by the image co-segmentation literature [7, 12, 1], we propose a symmetric Cross-Reference Network that two heads concurrently make predictions for both the query image and the support image.”
Unsupervised Joint Object Discovery and Segmentation in Internet Images (2013, methodology): “We compare our results with three previously proposed methods [8, 9, 12].”
Convex Deep Learning via Normalized Kernels (2014, background): “More recently, [23, 24] has considered learning kernel representations of latent clusters, achieving convex formulations under some relaxations.”
Finding Actors and Actions in Movies (2013, background): “Others have looked at convex relaxations of discriminative clustering with hidden variables for image co-segmentation [16, 17].”