RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions

By Ahmad Humayun, Fuxin Li, James M. Rehg. 2014

136 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

Learning to Segment Object Candidates (2015, methodology): “These approaches usually fall into three categories: (1) objectness scoring [1, 34], in which proposals are extracted by measuring the objectness score of bounding boxes, (2) seed segmentation [14, 16, 17], where models start with multiple seed regions and generate separate foreground-background seg”
What Makes for Effective Detection Proposals? (2015, methodology): “• In §4 we study object recall on the PASCAL VOC 2007 test set [4], and for the first time, over the larger and more diverse ImageNet 2013 [5] and MS COCO 2014 [6] validation sets.”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “Object proposals are a set of candidate regions or bounding boxes in an image that may potentially contain an object.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, methodology): “Top: original image, instance-level ground truth from COCO and our multiscale hierarchical segmentation.”
Recurrent Pixel Embedding for Instance Grouping (2017, methodology): “We compare against the most recent techniques including POISE [39], LPO [52], CPMC [8], GOP [51], SeSe [83], GLS [72], RIGOR [38].”
How good are detection proposals, really? (2014, background): “Rigor [20] is a variant of CPMC obtaining higher quality by using different low-level superpixels and different features for merging segments.”
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection (2017, background): “Our algorithm is superior than or on par with previous state-of-the-arts, including: BING (Cheng et al., 2014), EdgeBox (Zitnick and Dollar, 2014), GOP (Kra-henbuhl and Koltun, 2014), Selective Search (Uijlings et al., 2013), MCG (Arbel´aez et al., 2014), Endres (Endres and Hoiem, 2014), Prims (Man ”
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (2016, methodology): “These approaches include RIGOR [34] and MCG [35], which take 10 to 30 s per image and GOP [36], a faster methods that takes $1 s per image.”
BING: Binarized normed gradients for objectness estimation at 300fps (2014, unknown): “Compared to most popular alternatives [4, 26, 44, 49, 50, 61, 65–67, 75, 85, 90], our method achieves competitive performance using a smaller set of proposals, while being 100-1,000 times faster than them.”
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network (2016, methodology): “More related to our work is generating segmented object proposals [4, 10, 14, 24, 26, 29, 43].”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “A recent work in [98] pre-computes a graph which can be used for parametric min-cuts over different seeds, and then dynamic graph cut [99] is applied to accelerate the speed.”
Robust video segment proposals with painless occlusion handling (2015, methodology): “In our experiments, we use our RIGOR segmentation proposal algorithm [23], because it produces proposals quickly while maintaining good quality.”