Boosting Object Proposals: From Pascal to COCO

By Jordi Pont-Tuset, Luc Van Gool. 2015

60 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, methodology): “Many of the commonly used bounding box proposal methods [28, 54] first generate a set of overlapping segments, e.”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “Another recent related work is [60], which analyzes various methods in segment-based object proposals, focusing on the challenges faced when going from PASCAL VOC to MS COCO.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, methodology): “posal techniques, and their combination using the Pareto front optimization is studied in [44].”
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (2016, background): “Recent thorough comparisons of object proposal generation methods can be found in [56], [57].”
Object Counting and Instance Segmentation With Image-Level Supervision (2019, methodology): “For instance segmentation, the performance is evaluated using Average Best Overlap (ABO) [26] and mAP r, as in [34].”
Simple Does It: Weakly Supervised Instance and Semantic Segmentation (2016, methodology): “In general we can harness priors about object shape by using segment proposal techniques [35], which are designed to enumerate and rank plausible object shapes in an area of the image.”
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection (2017, background): “In recent years, CNN-based approaches (Hayder et al., 2016; Ghodrati et al., 2016; Pont-Tuset and Gool, 2015; He and Lau, 2015) are more popular with a non-trivial margin of performance boost.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2017, methodology): “The complementarity of MCG with respect to other proposal techniques, and their combination using the Pareto front optimization is studied in [44].”
Weakly Supervised Instance Segmentation Using Class Peak Response (2018, methodology): “The instance segmentation is evaluated with the mAP r at IoU threshold 0.25, 0.5 and 0.75, and the Average Best Overlap (ABO) [28] metric is also employed for evaluation to give a different perspective.”
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network (2016, background): “It is established in [23, 42] to benchmark the quality of bounding box and segmented object proposals.”