Figure-ground segmentation by transferring window masks

By Daniel Küttel, Vittorio Ferrari. 2012

122 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, background): “Additionally, it helps to clamp certain pixels to object [39].”
SoundNet: Learning Sound Representations from Unlabeled Video (2016, background): “Transfer Learning: Transfer learning is widely studied within computer vision such as transferring knowledge for object detection [1, 2] and segmentation [18], however transferring from vision to other modalities are only possible recently with the emergence of high performance visual models [33, 17”
CRF Learning with CNN Features for Image Segmentation (2015, methodology): “We use the same data split as in [5], [21], and we simply resize the images to 256 × 256.”
Semantic Object Selection (2014, methodology): “We pose the segmentation problem in a classic energy minimization framework [12, 20, 11].”
An Exemplar-Based CRF for Multi-instance Object Segmentation (2014, background): “[11] consider shape mask transfer from a training set for foreground object segmentation.”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, background): “We can not only exploit such simple appearance and geometry cues as model priors, but also go beyond to exploit a richer object hierarchy, which has been widely exploited in classification [16], [30], [31], [32] and to a less extent detection [7], [10].”
ImageNet Auto-Annotation with Segmentation Propagation (2014, methodology): “Our work weaves together and extends several recent developments including Grabcut [52], segmentation transfer [51,37], efﬁcient binary codes [27], cosegmentation [14,8] and structured output learning [65, 61] into a fully automatic, computationally efﬁcient and reliable large scale segmentation…”
Learning Discriminative Part Detectors for Image Classification and Cosegmentation (2013, background): “They represent objects or images by a set of important parts, and achieve state-of-the-art results for object detection [4, 15], action recognition [39], segmentation [2], etc. Learning these models has, however, been a challenge.”
SalientShape: group saliency in image collections (2013, background): “Kuettel and Ferrari [37] transfers segmentation mask from training windows that are visually similar to the target image windows.”
Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining (2016, methodology): “Inspired by the studies in [21], [38], and [39], the objectness [40] is used in this paper, which is trained on PASCAL VOC07 data set to distinguish windows containing an object with a well-”
Semantic Image Segmentation with Contextual Hierarchical Models (2015, background): “While some approaches such as [10], [11], [12], [13] can only be applied to edge detection problems and other approaches such as [14], [15], [16] are only designed for the image labeling problem, CHM can handle both problems equallywell without anymodification.”
Exemplar-Based Face Parsing (2013, background): “There are several recent scene parsing approaches in the literature that do not target faces, but nonetheless do share some aspects with our approach ([7, 8, 12, 19] to name just a few).”
Training Object Class Detectors from Eye Tracking Data (2014, methodology): “As Ms estimates the probability that superpixel s is on the object, this potential encourages the final segmentation to be close to M (see [26]).”
Shape Sharing for Object Segmentation (2012, methodology): “A contemporary approach uses window-level matching for more robust exemplar retrieval under image variations [24].”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “, unsupervised figure–ground segmentation (Yu and Shi 2003), and supervised figure–ground segmentation (Ren et al. 2006; Küttel and Ferrari 2012) to which could be turned from semantic segmentation by simply merging all the object labels into one class and the rest into the background.”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, background): “Additionally, it helps to clamp certain pixels to object [39].”
I Have Seen Enough: Transferring Parts Across Categories (2016, methodology): “Fewer works consider transfer learning for localization as we do; these include the works of [9, 19, 28, 33] that transfer bounding box information using the ImageNet hierarchies; the method of [22] that transfer object detectors from seed classes; and [1] which transfers detectors assuming a limite”