Multiscale Combinatorial Grouping

  title={Multiscale Combinatorial Grouping},
  author={Pablo Arbel{\'a}ez and Jordi Pont-Tuset and Jonathan T. Barron and Ferran Marqu{\'e}s and Jitendra Malik},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
We propose a unified approach for bottom-up hierarchical image segmentation and object candidate generation for recognition, called Multiscale Combinatorial Grouping (MCG). [] Key Method For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information.

Figures and Tables from this paper

Segmentation models diversity for object proposals

Image Segmentation Using Hierarchical Merge Tree

This paper uses a tree structure to represent the hierarchy of region merging to reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes, and forms a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier.

Making better use of edges via perceptual grouping

A perceptual grouping framework that organizes image edges into meaningful structures and demonstrates its usefulness on various computer vision tasks is proposed and shown how human-like sketches can be generated from edge groupings and consequently used to deliver state-of-the-art sketch-based image retrieval performance.

Image Segmentation Based on Similarity of Hierarchical Regions

  • Hongtao HeB. PengJunzhou Chen
  • Computer Science
    2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)
  • 2019
This paper uses the hidden regional properties of multi-level image segmentation, selecting the finer object segment regions through the comparison between hierarchies without the aid of ground truth or the users prior knowledge of the object, using the saliency of theobject for auxiliary analysis, and optimizing its combination.

Deep Grouping Model for Unified Perceptual Parsing

This work proposes a deep grouping model (DGM) that tightly marries the two types of representations and defines a bottom-up and a top-down process for feature exchanging and achieves state-of-the-art results while having a small computational overhead compared to other contextual-based segmentation models.

Revisiting graph construction for fast image segmentation

Learning to propose objects

The presented approach outperforms prior object proposal algorithms by a significant margin, while having the lowest running time, and generalize across datasets, indicating that the presented approach is capable of learning a generally applicable model of bottom-up segmentation.

Object proposal by multi-branch hierarchical segmentation

This work proposes a novel multi-branch hierarchical segmentation approach that alleviates problems by learning multiple merging strategies in each step in a complementary manner, such that errors in one merging strategy could be corrected by the others.

Segmentation of Objects by Hashing

This work uses the hierarchical structures first presented in [Arbelaez et al 2011] to use an efficient and accurate procedure that exploits the feature information of the hierarchy using Locality Sensitive Hashing and introduces a train-free alternative to Hypercolumns.



Bottom-Up Segmentation for Top-Down Detection

A novel deformable part-based model which exploits region-based segmentation algorithms that compute candidate object regions by bottom-up clustering followed by ranking of those regions that outperform the previous state-of-the-art on VOC 2010 test by 4%.

Image Segmentation by Cascaded Region Agglomeration

We propose a hierarchical segmentation algorithm that starts with a very fine over segmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights

SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning

SCALPEL is a flexible method for object segmentation that integrates rich region-merging cues with mid- and high-level information about object layout, class, and scale into the segmentation process and uses a cascade of bottom-up segmentation models that is capable of learning to ignore boundaries early on, yet use them as a stopping criterion once the object has been mostly segmented.

Semantic segmentation using regions and parts

A novel design for region-based object detectors that integrates efficiently top-down information from scanning-windows part models and global appearance cues is proposed that produces class-specific scores for bottom-up regions, and then aggregate the votes of multiple overlapping candidates through pixel classification.

Contour Detection and Hierarchical Image Segmentation

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector

CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts

A novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues and it is shown that the algorithm can be used, successfully, in a segmentation-based visual object category recognition pipeline.

Efficient Graph-Based Image Segmentation

An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.

Recognition using regions

This paper presents a unified framework for object detection, segmentation, and classification using regions using a generalized Hough voting scheme to generate hypotheses of object locations, scales and support, followed by a verification classifier and a constrained segmenter on each hypothesis.

Category-Independent Object Proposals with Diverse Ranking

  • Ian EndresDerek Hoiem
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2014
A category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects, demonstrating the ability to find most objects within a small bag of proposed regions.

Boundary Extraction in Natural Images Using Ultrametric Contour Maps

  • Pablo Arbeláez
  • Computer Science
    2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06)
  • 2006
This paper presents a low-level system for boundary extraction and segmentation of natural images and the evaluation of its performance proves that this system outperforms significantly two widely used hierarchical segmentation techniques, as well as the state of the art in local edge detection.