Edge Classification

13 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

IBM/EvolveGCN 26 Feb 2019

Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.

LaneNet: Real-Time Lane Detection Networks for Autonomous Driving

klintan/pytorch-lanenet 4 Jul 2018

Lane detection is to detect lanes on the road and provide the accurate location and shape of each lane.

Learning and Reasoning with the Graph Structure Representation in Robotic Surgery

mobarakol/Surgical_SceneGraph_Generation 7 Jul 2020

Learning to infer graph representations and performing spatial reasoning in a complex surgical environment can play a vital role in surgical scene understanding in robotic surgery.

Edge-augmented Graph Transformers: Global Self-attention is Enough for Graphs

shamim-hussain/egt_pytorch 7 Aug 2021

The resultant framework, which we call Edge-augmented Graph Transformer (EGT), can directly accept, process and output structural information as well as node information.

Dynamic Graph Convolutional Networks Using the Tensor M-Product


In recent years, a variety of graph neural networks (GNNs) have been successfully applied for representation learning and prediction on such graphs.

Shearlets as Feature Extractor for Semantic Edge Detection: The Model-Based and Data-Driven Realm

arsenal9971/shearlet_semantic_edge 27 Nov 2019

This is based on the fact that edges in images contain most of the semantic information.

Deep Multi-Scale Feature Learning for Defocus Blur Estimation

alikaraali/depthedgeawarebenet 24 Sep 2020

This paper presents an edge-based defocus blur estimation method from a single defocused image.

Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints

ayanc/edgeml.mdp 26 Oct 2020

To deploy machine learning-based algorithms for real-time applications with strict latency constraints, we consider an edge-computing setting where a subset of inputs are offloaded to the edge for processing by an accurate but resource-intensive model, and the rest are processed only by a less-accurate model on the device itself.

Unmixing Convolutional Features for Crisp Edge Detection

WHUHLX/CATS 19 Nov 2020

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.

Charged particle tracking via edge-classifying interaction networks

GageDeZoort/interaction_network_paper 30 Mar 2021

Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high energy particle physics.