Multiscale Combinatorial Grouping
We propose a unified approach for bottom-up hierarchical image segmentation and object candidate generation for recognition, called Multiscale Combinatorial Grouping (MCG). 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. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object candidates by exploring efficiently their combinatorial space. We conduct extensive experiments on both the BSDS500 and on the PASCAL 2012 segmentation datasets, showing that MCG produces state-of-the-art contours, hierarchical regions and object candidates.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationObjectSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normal…
Image SegmentationObjectObject Proposal GenerationSemantic SegmentationInstance-Level Salient Object Segmentation
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In thi…
Instance SegmentationObjectSaliency DetectionSegmentation+1GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence
Dynamically grouping sensory information into structured entities is essential for understanding the world of combinatorial nature. However, the grouping ability and therefore combinatorial generalization are still chall…
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object cont…
Contour DetectionDecoderEdge DetectionObjectMultiscale Random Fields with Application to Contour Grouping
We introduce a new interpretation of multiscale random fields (MSRFs) that admits efficient optimization in the framework of regular (single level) random fields (RFs). It is based on a new operator, called append, that …