Object cosegmentation

By Sara Alexandra Gomes Vicente, Carsten Rother, Vladimir Kolmogorov. 2011

324 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

What Makes for Effective Detection Proposals? (2015, background): “For example, they can be used to handle unknown categories at test time, or to enable weakly supervised learning [57], [58], [59].”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “Region proposals have been used in many of the methods discussed so far, but most of them [12, 27, 28, 42, 51, 54] use relatively a small number of the best proposals (typically, less than 100 for each image) to form whole object hypotheses, often together with generic objectness measures [1].”
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks (2019, methodology): “When processing an image, IOCS must leverage information from the whole image group (as the images are typically different and some are irrelevant) [49, 65].”
Unsupervised Joint Object Discovery and Segmentation in Internet Images (2013, methodology): “[25] introduced the notion of ”objectness” to the co-segmentation framework, showing that requiring the foreground segment to be an object often improves co-segmentation results significantly.”
Training Object Class Detectors from Eye Tracking Data (2014, methodology): “Weakly supervised methods train from a set of images labeled only as containing a certain object class, without location annotation [7,9,16,34,40,41,45].”
ImageNet Auto-Annotation with Segmentation Propagation (2014, methodology): “First, we validate the components of our approach on the smaller iCoseg dataset, we compare it to several existing works [8,34,71, 45] and achieve state-of-the-art performance (sec.”
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].”
CycleSegNet: Object Co-Segmentation With Cycle Refinement and Region Correspondence (2021, background): “Image cosegmentation algorithms have shown their usages in various computer vision tasks, such as image retrieval [38], 3D reconstruction [29], photo collections [33], image matching [6], [45], [46] and video object tracking and segmentation [23]–[25], [33].”
Learning Discriminative Part Detectors for Image Classification and Cosegmentation (2013, unknown): “Cosegmentation [19, 25, 34] is a challenging task in computer vision, since it involves a weak form of supervision, i.”
Multi-class cosegmentation (2012, background): “Unfortunately, most existing algorithms have only been demonstrated in rather restricted settings, involving only a pair of images at a time [3, 4], and/or only two foreground and background classes [5, 6, 7].”
Image Co-segmentation via Consistent Functional Maps (2013, methodology): “, jointly segmenting a collection of similar images, has received a good deal of attention recently in the vision literature [10, 24, 19].”
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts (2012, background): “[1], [79] as well as for multiregion image segmentation [3], [4] and cosegmentation [80].”
BiCoS: A Bi-level co-segmentation method for image classification (2011, background): “Co-segmentation of image collections has recently become a topic of active research [16, 19, 25, 31, 37, 38].”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “In [131], by representing each image as a set of object proposals, a random forest regression based model is learned to select the object from backgrounds.”
Unsupervised Multi-class Joint Image Segmentation (2014, background): “Vicente and colleagues [19] proposed to extract objects from a group of images by using an object recognition scheme to generate a pool of object-like segmentations, and then selecting the most likely segmentations using a learned pairwise consistency term.”
Segmentation Propagation in ImageNet (2012, unknown): “Importantly, our method is also computationally much more efficient than [15, 16].”