Instance-Level Segmentation with Deep Densely Connected MRFs

By Ziyu Zhang, Sanja Fidler, Raquel Urtasun. 2015

29 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Shape-aware Instance Segmentation (2016, background): “As such, it has many applications in diverse areas, such as autonomous driving [32], personal robotics [11] and plant analytics [27].”
Deep Watershed Transform for Instance Segmentation (2016, methodology): “Deep structured models: [30, 31] ﬁrst use CNNs to perform local instance disambiguation and labelling, followed by a global CRF to achieve instance label consistency.”
InstanceCut: From Edges to Instances with MultiCut (2016, background): “Another work, which focuses on instance segmentation of cars [55, 54] employs a conditional random field that reasons about instances using multiple overlapping outputs of an FCN.”
Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling (2016, methodology): “We clearly outperform all existing works on KITTI (Best [34]/[35]), c.”
Visual question answering: Datasets, algorithms, and future challenges (2016, background): “Instance segmentation further builds upon localization by differentiating between separate instances of the same semantic class [14, 15, 16].”
Asynchronous Temporal Fields for Action Recognition (2016, background): “In addition to being more suitable for stochastic training, fullyconnected models have shown increased performance on various tasks [18, 66].”
Boundary-Aware Instance Segmentation (2016, background): “This was further extended in [35] via a deep densely connected Markov Random Field.”
Joint Graph Decomposition and Node Labeling by Local Search (2016, background): “Instance-separating semantic segmentation [5, 6, 15, 22, 23, 24, 31, 32] is the task of assigning, to every point in an image, a label that identifies a class of objects (e.”
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications (2016, methodology): “Table 3: Comparison of algorithms for instance segmentation on the KITTI test dataset [2] using metrics proposed in [17].”
Box2Pix: Single-Shot Instance Segmentation by Assigning Pixels to Object Boxes (2018, methodology): “post-processing like graphical models [6], [8], clustering [9], [10] or template matching [11], [12] to gain high-level object knowledge.”
Monocular 3D Object Detection for Autonomous Driving (2016, methodology): “To compute instance-level segmentation we exploit the approach of [51, 50], which uses a CNN to create both instance-level pixel labeling as well as ordering in depth.”
LiDAR-Video Driving Dataset: Learning Driving Policies Effectively (2018, background): “Whereas, more works [1, 3, 29] used neural networks to solve relevant helpful problems such as semantic segmentation based on monocular images.”