“Clustering by Composition”—Unsupervised Discovery of Image Categories

By Alon Faktor, Michal Irani. 2012

94 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Unsupervised Visual Representation Learning by Context Prediction (2015, background): “Many other approaches [20, 27, 16] focus on defining similarity metrics which can be used in more standard clustering algorithms; [42], for instance, re-casts the problem as frequent itemset mining.”
Learning visual groups from co-occurrences in space and time (2015, methodology): “Grouping based on co-occurrence has received some prior attention in computer vision (Sivic et al. (2005); Faktor & Irani (2012; 2013); Isola et al. (2014)).”
Taskonomy: Disentangling Task Transfer Learning (2018, background): “compositional modeling [33, 8, 11, 21, 53, 89, 87], homomorphic cryptography [40], lifelong learning [90, 13, 82, 81], functional maps [68], certain aspects of Bayesian inference and Dirichlet processes [52, 88, 87, 86, 35, 37], few-shot learning [78, 23, 22, 67, 83], transfer learning [72, 81, 27, ”
Context as Supervisory Signal: Discovering Objects with Predictable Context (2014, background): “Proponents of unsupervised representation learning [1,2,3,4] and unsupervised object discovery [5,6,7,8,9,10,11,12] have long argued that these approaches have the potential to solve two fundamental problems with supervised methods.”
Category Modeling from Just a Single Labeling: Use Depth Information to Guide the Learning of 2D Models (2013, methodology): “Most methods used bag-of-words models [5] for category representation, and others [25, 26, 27, 28] detected repetitive objects with the similar appearance in the environment.”
Unsupervised Image Matching and Object Discovery as Optimization (2019, background): “, clustering [16]2, image matching [39] or topic discovery [41, 43] (see also [8, 11], where “pseudo-object” labels are learned in an unsupervised manner).”
Enriching Visual Knowledge Bases via Object Discovery and Segmentation (2014, methodology): “Finally, approaches have tried using other kind of priors including bounding boxes [20], context [19, 18], saliency [8] and object probability [2, 17, 15].”
Personal object discovery in first-person videos (2015, unknown): “Research about first-person video processing and understanding is also discussed.”
Weakly-supervised Discovery of Visual Pattern Configurations (2014, background): “Existing approaches discover high-level object categories [26, 12, 5], mid-level patches [22, 3, 14], or low-level foreground features [16] by grouping similar visual patterns (i.”
FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (2015, background): “More relevant to us, [24, 11, 34] perform joint object discovery and segmentation on a noisy image set, resulting in often excellent region-wise correspondences.”
Dataset fingerprints: Exploring image collections through data mining (2015, methodology): “A method that uses image affinity based on “similarity by composition” to discover object categories is presented in [8].”