Published on Mon Jan 09 2017

Information Pursuit: A Bayesian Framework for Sequential Scene Parsing

Ehsan Jahangiri, Erdem Yoruk, Rene Vidal, Laurent Younes, Donald Geman

Information Pursuit is a Bayesian framework for scene parsing. It combines prior models for the geometry of the scene and the spatial arrangement of objects. In the proposed framework, the scene interpretation is progressively refined.

0
0
0
Abstract

Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose Information Pursuit, a Bayesian framework for scene parsing that combines prior models for the geometry of the scene and the spatial arrangement of objects instances with a data model for the output of high-level image classifiers trained to answer specific questions about the scene. In the proposed framework, the scene interpretation is progressively refined as evidence accumulates from the answers to a sequence of questions. At each step, we choose the question to maximize the mutual information between the new answer and the full interpretation given the current evidence obtained from previous inquiries. We also propose a method for learning the parameters of the model from synthesized, annotated scenes obtained by top-down sampling from an easy-to-learn generative scene model. Finally, we introduce a database of annotated indoor scenes of dining room tables, which we use to evaluate the proposed approach.

Fri Sep 10 2010
Artificial Intelligence
Hierarchical Semi-Markov Conditional Random Fields for Recursive Sequential Data
The HSCRF is a generalisation of embedded undirectedMarkov chains. It is parameterised in a discriminative framework and has polynomial time algorithms for learning and inference. We show that it is capable of learning rich hierarchical models with reasonable accuracy.
0
0
0
Tue Feb 03 2015
Computer Vision
Data-Driven Scene Understanding with Adaptively Retrieved Exemplars
This article investigates a data-driven approach for semantically scene Understanding. Our framework parses a target image with two steps: retrieving its exemplars and recovering its pixel labels. We validate our approach on two public databases and demonstrate superior performances over the state-of-the-art methods.
0
0
0
Tue May 11 2021
Computer Vision
ORCEA: Object Recognition by Continuous Evidence Assimilation
0
0
0
Thu Jul 26 2018
Computer Vision
Unified Perceptual Parsing for Scene Understanding
Unified Perceptual Parsing requires machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations.
0
0
0
Thu Nov 26 2015
Computer Vision
A Computational Model for Amodal Completion
This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image. The estimated scene interpretation is obtained by integrating some global and local cues. The model is illustrated with numerical experiments on synthetic and real images.
0
0
0
Fri Sep 04 2015
Computer Vision
Semantic Amodal Segmentation
In this paper we look to the future: what is the next frontier in visual recognition? We propose a detailed image annotation that captures information beyond the visible pixels. We show that the proposed full scene annotation is surprisingly consistent between annotators.
0
0
0