EDeNN: Event Decay Neural Networks for low latency vision

• URL: http://arxiv.org/abs/2209.04362v2
• Date: Tue, 9 May 2023 14:22:17 GMT
• Title: EDeNN: Event Decay Neural Networks for low latency vision
• Authors: Celyn Walters, Simon Hadfield
• Abstract summary: We develop a new type of neural network which operates closer to the original event data stream. We demonstrate state-of-the-art performance in angular velocity regression and competitive optical flow estimation.
• Score: 26.784944204163363
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Despite the success of neural networks in computer vision tasks, digital 'neurons' are a very loose approximation of biological neurons. Today's learning approaches are designed to function on digital devices with digital data representations such as image frames. In contrast, biological vision systems are generally much more capable and efficient than state-of-the-art digital computer vision algorithms. Event cameras are an emerging sensor technology which imitates biological vision with asynchronously firing pixels, eschewing the concept of the image frame. To leverage modern learning techniques, many event-based algorithms are forced to accumulate events back to image frames, somewhat squandering the advantages of event cameras. We follow the opposite paradigm and develop a new type of neural network which operates closer to the original event data stream. We demonstrate state-of-the-art performance in angular velocity regression and competitive optical flow estimation, while avoiding difficulties related to training SNN. Furthermore, the processing latency of our proposed approach is less than 1/10 any other implementation, while continuous inference increases this improvement by another order of magnitude.

Related papers

• Training Robust Spiking Neural Networks with ViewPoint Transform and SpatioTemporal Stretching [4.736525128377909]
  We propose a novel data augmentation method, ViewPoint Transform and Spatio Stretching (VPT-STS) It improves the robustness of spiking neural networks by transforming the rotation centers and angles in thetemporal domain to generate samples from different viewpoints. Experiments on prevailing neuromorphic datasets demonstrate that VPT-STS is broadly effective on multi-event representations and significantly outperforms pure spatial geometric transformations.
  arXiv  Detail & Related papers  (2023-03-14T03:09:56Z)
• A neuromorphic approach to image processing and machine vision [0.9137554315375922]
  We explore the implementation of visual tasks such as image segmentation, visual attention and object recognition. We have emphasized on the employment of non-volatile memory devices such as memristors to realize artificial visual systems.
  arXiv  Detail & Related papers  (2022-08-07T05:01:57Z)
• Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision [64.71260357476602]
  Event-based vision sensors encode local pixel-wise brightness changes in streams of events rather than image frames. Recent progress in object recognition from event-based sensors has come from conversions of deep neural networks. We propose a hybrid architecture for end-to-end training of deep neural networks for event-based pattern recognition and object detection.
  arXiv  Detail & Related papers  (2021-12-06T23:45:58Z)
• Fast Training of Neural Lumigraph Representations using Meta Learning [109.92233234681319]
  We develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time. Our approach, MetaNLR++, accomplishes this by using a unique combination of a neural shape representation and 2D CNN-based image feature extraction, aggregation, and re-projection. We show that MetaNLR++ achieves similar or better photorealistic novel view synthesis results in a fraction of the time that competing methods require.
  arXiv  Detail & Related papers  (2021-06-28T18:55:50Z)
• Learning from Event Cameras with Sparse Spiking Convolutional Neural Networks [0.0]
  Convolutional neural networks (CNNs) are now the de facto solution for computer vision problems. We propose an end-to-end biologically inspired approach using event cameras and spiking neural networks (SNNs) Our method enables the training of sparse spiking neural networks directly on event data, using the popular deep learning framework PyTorch.
  arXiv  Detail & Related papers  (2021-04-26T13:52:01Z)
• Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks [82.54695985117783]
  We investigate the suitability of state-of-the-art deep learning architectures for continuous emotion recognition using long video sequences captured in-the-wild. We have developed and evaluated convolutional recurrent neural networks combining 2D-CNNs and long short term-memory units, and inflated 3D-CNN models, which are built by inflating the weights of a pre-trained 2D-CNN model during fine-tuning.
  arXiv  Detail & Related papers  (2020-11-18T13:42:05Z)
• 11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks [0.0]
  We demonstrate a universal optical vector convolutional accelerator operating beyond 10 TeraFLOPS (floating point operations per second) We then use the same hardware to sequentially form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 900 pixel handwritten digit images with 88% accuracy. This approach is scalable and trainable to much more complex networks for demanding applications such as unmanned vehicle and real-time video recognition.
  arXiv  Detail & Related papers  (2020-11-14T21:24:01Z)
• Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy [0.0]
  Event cameras are novel vision sensors that sample, in an asynchronous fashion, brightness increments with low latency and high temporal resolution. We propose a novel, lightweight neural network for optical flow estimation that achieves high speed inference with only a minor drop in performance. Results across multiple datasets show that the performance of the proposed self-supervised approach is in line with the state-of-the-art.
  arXiv  Detail & Related papers  (2020-09-17T13:30:05Z)
• Neural Sparse Representation for Image Restoration [116.72107034624344]
  Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
  arXiv  Detail & Related papers  (2020-06-08T05:15:17Z)
• Event-based Asynchronous Sparse Convolutional Networks [54.094244806123235]
  Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse "events" We present a general framework for converting models trained on synchronous image-like event representations into asynchronous models with identical output. We show both theoretically and experimentally that this drastically reduces the computational complexity and latency of high-capacity, synchronous neural networks.
  arXiv  Detail & Related papers  (2020-03-20T08:39:49Z)
• Event-Based Angular Velocity Regression with Spiking Networks [51.145071093099396]
  Spiking Neural Networks (SNNs) process information conveyed as temporal spikes rather than numeric values. We propose, for the first time, a temporal regression problem of numerical values given events from an event camera. We show that we can successfully train an SNN to perform angular velocity regression.
  arXiv  Detail & Related papers  (2020-03-05T17:37:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.