Discriminative clustering for image co-segmentation

By Armand Joulin, Francis R. Bach, Jean Ponce. 2010

504 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): “Examples include: unsupervised learning from narrated instruction videos [1], text-to-video alignment [6], co-segmentation [16], co-localization in videos and images [18] or instance-level segmentation [31], which can be now scaled-up to an order of magnitude larger datasets.”
Deep Clustering for Unsupervised Learning of Visual Features (2018, methodology): “Unsupervised learning has been widely studied in the Machine Learning community [19], and algorithms for clustering, dimensionality reduction or density estimation are regularly used in computer vision applications [27, 54, 60].”
Unsupervised Learning by Predicting Noise (2017, methodology): “It has been successfully applied to several computer vision applications, like object discovery (Joulin et al., 2010; Tang et al., 2014) or video/text alignment (Bojanowski et al., 2013; 2014; Ra-manathan et al., 2014).”
What's the Point: Semantic Segmentation with Point Supervision (2015, methodology): “[14, 36, 37] use co-segmentation methods trained from image-level labels to automatically infer the segmentations.”
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): “On the other hand, cosegmentation [25, 29, 40] and colocalization [12, 27, 51] assume less supervision and only require the image collection to contain a single dominant object class, allowing noisy images to some degree.”
Webly Supervised Semantic Segmentation (2017, methodology): “[40] 37.”
Object cosegmentation (2011, methodology): “The methods in [15, 23] can be considered as state-of-theart.”
Enriching Visual Knowledge Bases via Object Discovery and Segmentation (2014, background): “Our work is also related to co-segmentation, where the task is to simultaneously segment visually similar objects from multiple images at the same time [29, 28, 3, 11, 13, 36].”
Instance-Level Video Segmentation from Object Tracks (2016, methodology): “Semantic object segmentation in images and videos is a challenging computer vision task [24, 29, 31, 39, 45].”
Efficient Image and Video Co-localization with Frank-Wolfe Algorithm (2014, methodology): “Our work builds upon the formulation introduced in [44] for co-localization in images, which defines an optimization objective that draws inspiration from works in image segmentation [42] and discriminative clustering [3, 21, 49, 51].”
Image Co-segmentation via Consistent Functional Maps (2013, methodology): “8a, in comparison with other recent co-segmentation algorithms [10] and [19].”
Unsupervised Multi-class Joint Image Segmentation (2014, methodology): “[8], [6] and [16] are applied to each subgroup of images which share the same foregrounds.”
Detection of Co-salient Objects by Looking Deep and Wide (2016, methodology): “Specifically, Joulin et al. (2010) adopted the discriminative clustering to introduce the spatial and local color consistency constraints into the partitions found by the clustering algorithm to separate the foreground and background. However, they need human labor to select the best candidate by ha”
Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-Grained Image Classification (2017, methodology): “Existing co-segmentation methods (Rubinstein et al. 2013; Joulin, Bach, and Ponce 2010) typically assume that the bounding box of the object is not available, while we have gotten the bounding box through the saliency extraction process, which is helpful even though it is not accurate enough.”
An Exact Penalty Method for Binary Optimization Based on MPEC Formulation (2017, unknown): “…graph matching (Cour, Srinivasan, and Shi, 2007; Toshev, Shi, and Daniilidis, 2007; Zaslavskiy, Bach, and Vert, 2009), image (co-)segmentation (Shi and Malik, 2000; Joulin, Bach, and Ponce, 2010), image Copyright c© 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org).”
Co-localization in Real-World Images (2014, methodology): “Following [15], we consider the ridge regression objective function for our boxes:”
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation (2020, background): “[53] simply applies off-the-shelf co-segmentation [25] over the web images to generate foreground priors, instead of ours encoding the semantic relations into network learning and inference.”