Abstract
Our aim is to provide a pixel-wise instance-level labeling of a monocular image in the context of autonomous driving. We build on recent work [32] that trained a convolutional neural net to predict instance labeling in local image patches, extracted exhaustively in a stride from an image. A simple Markov random field model using several heuristics was then proposed in [32] to derive a globally consistent instance labeling of the image. In this paper, we formulate the global labeling problem with a novel densely connected Markov random field and show how to encode various intuitive potentials in a way that is amenable to efficient mean field inference [15]. Our potentials encode the compatibility between the global labeling and the patch-level predictions, contrast-sensitive smoothness as well as the fact that separate regions form different instances. Our experiments on the challenging KITTI benchmark [8] demonstrate that our method achieves a significant performance boost over the baseline [32].
Keywords
Markov random fieldComputer scienceENCODEArtificial intelligenceConvolutional neural networkConditional random fieldPattern recognition (psychology)Image segmentationSegmentationHeuristicsMarkov chainInferencePixelComputer visionMachine learning
Affiliated Institutions
Related Publications
Learning Hierarchical Features for Scene Labeling
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network traine...
FCOS: Fully Convolutional One-Stage Object Detection
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all stat...
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, ex...
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a mu...
Publication Info
- Year
- 2016
- Type
- preprint
- Citations
- 206
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
206
OpenAlex
Cite This
Ziyu Zhang,
Sanja Fidler,
Raquel Urtasun
(2016).
Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs.
.
https://doi.org/10.1109/cvpr.2016.79
Identifiers
- DOI
- 10.1109/cvpr.2016.79