2012
NIPS
NeurIPS 2012
A Generative Model for Parts-based Object Segmentation
Abstract
The Shape Boltzmann Machine (SBM) has recently been introduced as a state-of-the-art model of foreground/background object shape. We extend the SBM to account for the foreground object's parts. Our model, the Multinomial SBM (MSBM), can capture both local and global statistics of part shapes accurately. We combine the MSBM with an appearance model to form a fully generative model of images of objects. Parts-based image segmentations are obtained simply by performing probabilistic inference in the model. We apply the model to two challenging datasets which exhibit significant shape and appearance variability, and find that it obtains results that are comparable to the state-of-the-art.
🌉
Interdisciplinary Bridge
— Computer Vision and Deep Learning
📈
Trend Setter
— Image Segmentation
🧭
Keyword Pioneer
— shape boltzmann machine
🐣
Hot Topic Early Bird
— generative model
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Deep Learning > Models > Generative Models
Computer Vision > Analysis > Object Detection
Computer Vision > Processing > Image Segmentation
Computer Vision > Processing > Semantic Segmentation
Machine Learning > Learning Types > Deep Learning
Computer Vision > Analysis > Object Segmentation
Machine Learning > Learning Types > Generative Models