CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts

By João Carreira, Cristian Sminchisescu. 2012

680 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

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015, methodology): “, Selective Search [4], CPMC [22], MCG [23]) and those based on sliding windows (e.”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “We followed the same protocol of submitting test results to the ILSVRC2013 evaluation server only twice, once with and once without bounding-box regression.”
Instance-Aware Semantic Segmentation via Multi-task Network Cascades (2015, methodology): “These methods all require mask proposal methods [29, 3, 1] that are slow at inference time.”
What Makes for Effective Detection Proposals? (2015, methodology): “Sliding window classifiers scale linearly with the number of windows tested, and while single-scale detection requires classifying around 104 – 105 windows per image, the number of windows grows by an order of magnitude for multi-scale detection.”
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, background): “Substantial improvements have been achieved by incorporating richer information from context [45] and structured prediction techniques [22], [26], [27], [46], but the performance of these systems has always been compromised by the limited expressive power of the features.”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “Types of Object Proposals: Object proposals can be broadly categorized into two categories: • Window scoring : In these methods, the space of all possible windows in an image is sampled to get a sub-set of the windows ( e.g ., via sliding window).”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “A celebrated non-DCNN precursor to these works is the second order pooling method of (Carreira et al., 2012) which also assigns labels to the regions proposals delivered by (Carreira & Sminchisescu, 2012).”
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture (2014, methodology): “Prior work on semantic segmentation includes many different approaches, both using RGB-only data [35, 4, 9] as well as RGB-D [31, 29, 26, 6, 15, 17, 13].”
ParseNet: Looking Wider to See Better (2015, methodology): “Followed by the proposal + post-classification scheme [30, 1], CNNs achieve state-ofthe-art results on object detection and segmentation tasks.”
Feedforward semantic segmentation with zoom-out features (2014, background): “Another recent trend has been to follow a multi-stage approach: First a set of proposal regions is generated, by a category-independent [6, 38] or category-aware [2] mechanism.”
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation (2015, methodology): “We resort to region proposal methods [4, 33, 2] to generate candidate segmentation masks.”
Multi-view 3D Object Detection Network for Autonomous Driving (2016, methodology): “3D Object Proposals Similarly to 2D object proposals [21, 29, 2], 3D object proposal methods generate a small set of 3D candidate boxes in order to cover most of the objects in 3D space.”
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation (2015, background): “, CPMC [3] and MCG [1], learned on pixel-segmented images.”
HCP: A Flexible CNN Framework for Multi-Label Image Classification (2014, background): “methods [1], [2], [4], [9], [38], [44] have been proposed to generate a set of hypotheses to cover all independent objects in a given image.”
R-CNN minus R (2015, methodology): “All such methods rely not only on CNNs, but also on a region proposal generation mechanism such as SS [18], CPMC [3], multi-scale combinatorial grouping [2], and edge boxes [23].”
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, methodology): “An overview of this approach is shown in Fig.1 At the testing stage, the AlexNet in [29] is used for extracting features from bounding boxes, then 200 oneversus-all linear classifiers are used for deciding the existence of object in these bounding boxes.”