Iterative Spectral Clustering for Unsupervised Object Localization
This addresses the problem of localizing objects without annotations for researchers in computer vision, though it is incremental as it builds on spectral clustering methods.
The paper tackles unsupervised object localization in images by proposing iterative spectral clustering with a cluster selection strategy to find object regions, achieving average CorLoc percentages of 51% on Object Discovery and 35% on PASCAL VOC 2007.
This paper addresses the problem of unsupervised object localization in an image. Unlike previous supervised and weakly supervised algorithms that require bounding box or image level annotations for training classifiers in order to learn features representing the object, we propose a simple yet effective technique for localization using iterative spectral clustering. This iterative spectral clustering approach along with appropriate cluster selection strategy in each iteration naturally helps in searching of object region in the image. In order to estimate the final localization window, we group the proposals obtained from the iterative spectral clustering step based on the perceptual similarity, and average the coordinates of the proposals from the top scoring groups. We benchmark our algorithm on challenging datasets like Object Discovery and PASCAL VOC 2007, achieving an average CorLoc percentage of 51% and 35% respectively which is comparable to various other weakly supervised algorithms despite being completely unsupervised.