A Novel Knowledge-Compatibility Benchmarker for Semantic Segmentation

  title={A Novel Knowledge-Compatibility Benchmarker for Semantic Segmentation},
  author={Vektor Dewanto and Aprinaldi and Zulfikar Ian and Wisnu Jatmiko},
  journal={International Journal on Smart Sensing and Intelligent Systems},
  pages={1284 - 1312}
Abstract The quality of a semantic annotation is typically measured with its averaged class-accuracy value, whose computation requires scarce ground-truth annotations. We observe that humans accumulate knowledge through their vision and believe that the quality of a semantic annotation is proportionally related to its compatibility with the vision-based knowledge. We propose a knowledge-compatibility benchmarker, whose backbone is a regression machine. It takes as input a semantic annotation… 

Figures and Tables from this paper

Learning semantic segmentation score in weakly supervised convolutional neural network

This research proposes a model to predict score of annotation accuracy of semantic segmentation based on bag level information without the availability of pixel level annotation.

Lightweight Semantic Segmentation Convolutional Neural Network Based on SKNet

Ellipse Detection on Embryo Imaging Using Random Sample Consensus (Ransac) Method Based on Arc Segment

RANSAC method based on Arc Segment to automatically detect embryo can detect single and multiple ellipse on embryo with a better accuracy than the previous method, EDCircles by 6%c and 3%c for single and double respectively.



Large-scale semantic co-labeling of image sets

This paper introduces a semantic co-labeling approach that performs efficient inference in a fully-connected CRF defined over the pixels, or superpixels, of an image set.

Decomposing a scene into geometric and semantically consistent regions

A region-based model which combines appearance and scene geometry to automatically decompose a scene into semantically meaningful regions and which achieves state-of-the-art performance on the tasks of both multi-class image segmentation and geometric reasoning.

Fusing Global and Local Scale for Semantic Image Segmentation

A new harmony potential is proposed that can encode any possible com- bination of labels, penalizing only unlikely combinations of classes, and also proposes an effective sampling strategy over this expanded label set that renders tractable the underlying optimization problem.

Exploiting hierarchical context on a large database of object categories

This paper introduces a new dataset with images that contain many instances of different object categories and proposes an efficient model that captures the contextual information among more than a hundred ofobject categories and shows that the context model can be applied to scene understanding tasks that local detectors alone cannot solve.

TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

A new approach for learning a discriminative model of object classes, incorporating texture, layout, and context information efficiently, which gives competitive and visually pleasing results for objects that are highly textured, highly structured, and even articulated.

Associative hierarchical CRFs for object class image segmentation

This work proposes a hierarchical random field model, that allows integration of features computed at different levels of the quantisation hierarchy, and evaluates its efficiency on some of the most challenging data-sets for object class segmentation, and shows it obtains state-of-the-art results.

Objects in Context

This work proposes to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model using a conditional random field (CRF) framework, which maximizes object label agreement according to contextual relevance.

Multi-Class Segmentation with Relative Location Prior

This work proposes a method for capturing global information from inter-class spatial relationships and encoding it as a local feature and shows that the incorporation of relative location information allows it to significantly outperform the current state-of-the-art.

Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers

This work simultaneously learns the visual features defining "nouns" and the differentialVisual features defining such "binary-relationships" using an EM-based approach and constrain the correspondence problem by exploiting additional language constructs to improve the learning process from weakly labeled data.

Superpixel Graph Label Transfer with Learned Distance Metric

This work presents a fast approximate nearest neighbor algorithm for semantic segmentation that builds a graph over superpixels from an annotated set of training images and proposes to learn a distance metric that weights the edges in the graph.