A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation
Superpixel-based Higher-order Conditional random fields (SP-HO-CRFs) are known for their effectiveness in enforcing both short and long spatial contiguity for pixelwise labelling in computer vision. However, their higher-order potentials are usually too complex to learn and often incur a high computational cost in performing inference. We propose an new approximation approach to SP-HO-CRFs that resolves these problems. Our approach is a multi-layer CRF framework that inherits the simplicity from pairwise CRFs by formulating both the higher-order and pairwise cues into the same pairwise potentials in the first layer. Essentially, this approach provides accuracy enhancement on the basis of pairwise CRFs without training by reusing their pre-trained parameters and/or weights. The proposed multi-layer approach performs especially well in delineating the boundary details (boarders) of object categories such as "trees" and "bushes". Multiple sets of experiments conducted on dataset MSRC-21 and PASCAL VOC 2012 validate the effectiveness and efficiency of the proposed methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation
Superpixel-based Higher-order Conditional Random Fields (CRFs) are effective in enforcing long-range consistency in pixel-wise labeling problems, such as semantic segmentation. However, their major short coming is consid…
Semantic SegmentationHigher Order Conditional Random Fields in Deep Neural Networks
We address the problem of semantic segmentation using deep learning. Most segmentation systems include a Conditional Random Field (CRF) to produce a structured output that is consistent with the image's visual features. …
SegmentationSemantic SegmentationSuperpixelsSuperpixel-based Knowledge Infusion in Deep Neural Networks for Image Classification
Superpixels are higher-order perceptual groups of pixels in an image, often carrying much more information than the raw pixels. There is an inherent relational structure to the relationship among different superpixels of…
Face RecognitionGraph Neural Networkimage-classificationImage Classification+2Hierarchical Piecewise-Constant Super-regions
Recent applications in computer vision have come to heavily rely on superpixel over-segmentation as a pre-processing step for higher level vision tasks, such as object recognition, image labelling or image segmentation. …
DenoisingFormImage SegmentationObject Recognition+3Fuzzy Superpixel-based Image Segmentation
This article presents a multi-phase image segmentation methodology based on fuzzy superpixel decomposition, aggregation and merging. First, a collection of layers of dense fuzzy superpixels is generated by the variationa…
Image SegmentationSegmentationSemantic SegmentationSuperpixels