paper-with-me

홈 › Papers

Scene Labeling Through Knowledge-Based Rules Employing Constrained Integer Linear Programing

2016-08-17 · Nasim Souly, Mubarak Shah

Scene labeling task is to segment the image into meaningful regions and categorize them into classes of objects which comprised the image. Commonly used methods typically find the local features for each segment and label them using classifiers. Afterward, labeling is smoothed in order to make sure that neighboring regions receive similar labels. However, they ignore expressive and non-local dependencies among regions due to expensive training and inference. In this paper, we propose to use high-level knowledge regarding rules in the inference to incorporate dependencies among regions in the image to improve scores of classification. Towards this aim, we extract these rules from data and transform them into constraints for Integer Programming to optimize the structured problem of assigning labels to super-pixels (consequently pixels) of an image. In addition, we propose to use soft-constraints in some scenarios, allowing violating the constraint by imposing a penalty, to make the model more flexible. We assessed our approach on three datasets and obtained promising results.

📄 PDF Abstract BibTeX arXiv:1608.05104

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Labeling

Similar Papers 제목 키워드 기반

Ruler: Data Programming by Demonstration for Document Labeling

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Sara Evensen, Chang Ge, Cagatay Demiralp

Data programming aims to reduce the cost of curating training data by encoding domain knowledge as labeling functions over source data. As such it not only requires domain expertise but also programming experience, a ski…

Explainability-Driven Quality Assessment for Rule-Based Systems

2025-02-03 · Oshani Seneviratne, Brendan Capuzzo, William Van Woensel

This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems based on dataset-driven insights. The traditional method for rule induction from data typically…

counterfactualDecision MakingFairness

Image Parsing with Stochastic Scene Grammar

2011-12-01 · NeurIPS 2011 12 · Yibiao Zhao, Song-Chun Zhu

This paper proposes a parsing algorithm for scene understanding which includes four aspects: computing 3D scene layout, detecting 3D objects (e.g. furniture), detecting 2D faces (windows, doors etc.), and segmenting back…

ClusteringScene LabelingScene Understanding

Knowledge-Driven Self-Supervised Representation Learning for Facial Action Unit Recognition

2022-01-01 · CVPR 2022 1 · Yanan Chang, Shangfei Wang

Facial action unit (AU) recognition is formulated as a supervised learning problem by recent works. However, the complex labeling process makes it challenging to provide AU annotations for large amounts of facial ima…

Contrastive LearningFacial Action Unit DetectionRepresentation Learning

GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition

2021-04-13 · EACL 2021 2 · Xinyan Zhao, Haibo Ding, Zhe Feng

Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling rules is challenging because it often re…

Graph Neural Networknamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2