Neuromorphic Imaging and Classification with Graph Learning
Not on the map. Why?
Abstract (arXiv)
Bio-inspired neuromorphic cameras asynchronously record pixel brightness changes and generate sparse event streams. They can capture dynamic scenes with little motion blur and more details in extreme illumination conditions. Due to the multidimensional address-event structure, most existing vision algorithms cannot properly handle asynchronous event streams. While several event representations and processing methods have been developed to address such an issue, they are typically driven by a large number of events, leading to substantial overheads in runtime and memory. In this paper, we propose a new graph representation of the event data and couple it with a Graph Transformer to perform accurate neuromorphic classification. Extensive experiments show that our approach leads to better results and excels at the challenging realistic situations where only a small number of events and limited computational resources are available, paving the way for neuromorphic applications embedded into mobile facilities.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 27 Sep 2023.
Builds on
33 of 49 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2019Event-based Vision: A Surveycited by 1,016
21 more
- 2020Simple and Deep Graph Convolutional Networkscited by 860
- 2021How Attentive are Graph Attention Networks?cited by 835
- 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
- 2019Self-Attention Graph Poolingcited by 421
- 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
- 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
- 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
- 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
- 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
- 2018Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Carscited by 200
- 2020Learning to Detect Objects with a 1 Megapixel Event Cameracited by 186
- 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
- 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 161
- 2019ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representationscited by 156
- 2016Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequencescited by 99
- 2021N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Camerascited by 92
- 2019Graph-Based Object Classification for Neuromorphic Vision Sensingcited by 85
- 2019SNODE: Spectral Discretization of Neural ODEs for System Identificationcited by 26
- 2022Exploiting Spatial Sparsity for Event Cameras with Visual Transformerscited by 23
- 2021Pyramidal Reservoir Graph Neural Networkcited by 10
- 2020Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEscited by 4
Built on by
Citing papers per year: 2024: 3.
3 papers.