Unsupervised Joint Object Discovery and Segmentation in Internet Images

By Michael Rubinstein, Armand Joulin, Johannes Peter Kopf, Ce Liu. 2013

390 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

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era (2017, background): “In order to overcome the bottleneck, there have been recent efforts on visual representation learning using web-supervision [2, 5, 6, 9, 21, 23, 24, 27] or unsupervised [10, 11, 31, 32, 34, 42, 43] paradigms.”
Learning Visual Features from Large Weakly Supervised Data (2015, background): “This study is not the ﬁrst to explore alternatives to training convolutional networks on manually annotated datasets [6, 10, 41, 59].”
Learning Open-World Object Proposals without Learning to Classify (2021, background): “They have become the integral pre-processing steps for many computer vision systems, including object detection [33,41,42,45,59,74], segmentation [3,8,13], object discovery [12, 16, 47], weakly supervised object detection [5, 21, 53], visual tracking [35, 63], content-aware retargeting [51], etc.”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “Notice that the former definition has an emphasis on object discovery [27,28,30], while the latter definition emphasises on the ultimate performance of a detection pipeline.”
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.”
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.”
Efficient Image and Video Co-localization with Frank-Wolfe Algorithm (2014, background): “Recent research has studied ways of leveraging this data, such as weakly supervised localization [14], co-segmentation [21, 23, 38], and co-localization [37, 44].”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, background): “The work of [21, 41] focuses on discovering commonly occurring segments within a large pool of web images, but does not report localization results.”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, methodology): “generalisable model for tasks such as object classification [4], detection [5], [6], and segmentation [3], [7], [8].”
Convolutional Neural Network Architecture for Geometric Matching (2017, background): “Estimating correspondences between images is one of the fundamental problems in computer vision [20, 26] with applications ranging from large-scale 3D reconstruction [2] to image manipulation [22] and semantic segmentation [44].”
Deep ViT Features as Dense Visual Descriptors (2021, methodology): “Several unsupervised methods used hand-crafted descriptors [15,44,45] for this task.”
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection (2015, methodology): “Furthermore, we applied our method for object cosegmentation in a large scale dataset [43] which contains thousands of noisy internet images.”
Fine-grained recognition without part annotations (2015, background): “Co-segmentation, the task of segmenting the object common to a set of images, has made great strides in recent years [22, 38, 24, 9, 11, 10, 29].”
Learning About Objects by Learning to Interact with Them (2020, background): “[51] propose an unsupervised approach to discover objects in a collection of web images.”
CRNet: Cross-Reference Networks for Few-Shot Segmentation (2020, background): “[16] capture the sparsity and visual variability of the common object from pairs of images with dense correspondences.”
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.”
Co-localization in Real-World Images (2014, methodology): “notation noise [24, 30, 31], most previous works related to co-localization have assumed clean labels, which is not a realistic assumption in many real-world settings where we have to analyze large numbers of Internet images or discover objects with roaming robots.”
Semantic Object Selection (2014, methodology): “In fact, Rubenstein et al. [21] propose a method designed to cosegment sets of images collected from an Internet search.”