Paper Info
Title
Beyond Grids - Learning Graph Representations for Visual Recognition.
Abstract
We propose learning graph representations from 2D feature maps for visual recognition. Our method draws inspiration from region based recognition, and learns to transform a 2D image into a graph structure. The vertices of the graph define clusters of pixels ("regions"), and the edges measure the similarity between these clusters in a feature space. Our method further learns to propagate information across all vertices on the graph, and is able to project the learned graph representation back into 2D grids. Our graph representation facilitates reasoning beyond regular grids and can capture long range dependencies among regions. We demonstrate that our model can be trained from end-to-end, and is easily integrated into existing networks. Finally, we evaluate our method on three challenging recognition tasks: semantic segmentation, object detection and object instance segmentation. For all tasks, our method outperforms state-of-the-art methods.
Year
Venue
Field
2018
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018)
Object detection,Graph,Feature vector,Vertex (geometry),Pattern recognition,Segmentation,Computer science,Visual recognition,Pixel,Artificial intelligence,Graph (abstract data type),Machine learning
DocType
Volume
ISSN
Conference
31
1049-5258
Citations 
PageRank 
References 
7
0.40
0
Authors
2
Name
Order
Citations
PageRank
Yin Li179735.85
Abhinav Gupta24692234.95