Learning to propose objects

By Philipp Krahenbuhl, Vladlen Koltun. 2015

88 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

Learning to Segment Object Candidates (2015, background): “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”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “More recently, object proposals are increasingly viewed as detection proposals [1, 8, 11, 42] where the goal is to improve the object detection pipeline, focusing on a chosen set of object classes (e.”
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization (2016, background): “Several approaches have been proposed in the literature for this task [1, 2, 5, 6, 8, 18, 25, 26, 29, 40, 44].”
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].”
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline (2022, methodology): “Ensembles of models have long been utilized to improve the performance in computer vision [19, 33, 35, 51, 55, 45].”
Simple Does It: Weakly Supervised Instance and Semantic Segmentation (2016, background): “Object proposals [35, 16] that generate segments (such as [34, 21]) can be used for instance segmentation.”
LocNet: Improving Localization Accuracy for Object Detection (2015, background): “…on object detection, treats the object localization problem at pre-recognition level by incorporating category-agnostic object proposal algorithms [35, 40, 26, 1, 18, 19, 2, 34, 33] that given an image, try to generate candidate boxes with high recall of the ground truth objects that they cover.”
BING: Binarized normed gradients for objectness estimation at 300fps (2014, unknown): “We extensively evaluate our method on the challenging PASCAL VOC2007 [27] and Microsoft COCO [56] [26], Objectness [4], GOP [49], LPO [50], Rahtu [66], RandomPrim [61], Rantalankila [67], and SelectiveSearch [75] 7 using publicly available code.”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, background): “Finally, unlike [15, 27, 41, 38], which learn to propose objects either in videos or static images, our approach does not require any labeled video/image to train and instead adapts to each unknown object on a per-video basis.”
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (2016, background): “of local and global CRFs [12] or minimizing parametric energies that encode mid-level cues such as symmetry and closure [13].”
Reinforcement Learning for Visual Object Detection (2016, methodology): “Typical methodologies include parametric figureground segmentation with Gestalt, 'object-like' filtering[5], superpixels[38] [32] or edge-based cues[21].”
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network (2016, background): “It turns out that the CEDNMCG achieves a competitive AR to MCG with a slightly lower recall from fewer proposals, but a weaker ABO than LPO, MCG and SeSe.”
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection (2017, methodology): “In (Krahenbuhl and Koltun, 2015), a learning method is proposed by”
Monocular 3D Object Detection for Autonomous Driving (2016, background): “The most recent line of work aims to learn how to propose promising object candidates using either ensembles of binary segmentation models [27], parametric energies [29] or window classifiers based on CNN features [18].”