EventMix: An Efficient Augmentation Strategy for Event-Based Data
- URL: http://arxiv.org/abs/2205.12054v1
- Date: Tue, 24 May 2022 13:07:33 GMT
- Title: EventMix: An Efficient Augmentation Strategy for Event-Based Data
- Authors: Guobin Shen, Dongcheng Zhao, Yi Zeng
- Abstract summary: Event cameras can provide high dynamic range and low-energy event stream data.
The scale is smaller and more difficult to obtain than traditional frame-based data.
This paper proposes an efficient data augmentation strategy for event stream data: EventMix.
- Score: 4.8416725611508244
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: High-quality and challenging event stream datasets play an important role in
the design of an efficient event-driven mechanism that mimics the brain.
Although event cameras can provide high dynamic range and low-energy event
stream data, the scale is smaller and more difficult to obtain than traditional
frame-based data, which restricts the development of neuromorphic computing.
Data augmentation can improve the quantity and quality of the original data by
processing more representations from the original data. This paper proposes an
efficient data augmentation strategy for event stream data: EventMix. We
carefully design the mixing of different event streams by Gaussian Mixture
Model to generate random 3D masks and achieve arbitrary shape mixing of event
streams in the spatio-temporal dimension. By computing the relative distances
of event streams, we propose a more reasonable way to assign labels to the
mixed samples. The experimental results on multiple neuromorphic datasets have
shown that our strategy can improve its performance on neuromorphic datasets
both for ANNs and SNNs, and we have achieved state-of-the-art performance on
DVS-CIFAR10, N-Caltech101, N-CARS, and DVS-Gesture datasets.
Related papers
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision [9.447299017563841]
Event data offers a unique approach to visual processing, showcasing its efficiency in dynamic and real-time scenarios.
Despite advantages such as high temporal resolution and low energy consumption, the application of event data faces challenges due to limited dataset size and diversity.
We develop EventZoom, a data augmentation strategy specifically designed for event data.
arXiv Detail & Related papers (2024-05-29T08:39:31Z) - Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models [2.551844666707809]
Event-based sensors are well suited for real-time processing.
Current methods either collapse events into frames or cannot scale up when processing the event data directly event-by-event.
arXiv Detail & Related papers (2024-04-29T08:50:27Z) - An Event-Oriented Diffusion-Refinement Method for Sparse Events
Completion [36.64856578682197]
Event cameras or dynamic vision sensors (DVS) record asynchronous response to brightness changes instead of conventional intensity frames.
We propose an inventive event completion sequence approach conforming to unique characteristics of event data in both the processing stage and the output form.
Specifically, we treat event streams as 3D event clouds in thetemporal domain, develop a diffusion-based generative model to generate dense clouds in a coarse-to-fine manner, and recover exact timestamps to maintain the temporal resolution of raw data successfully.
arXiv Detail & Related papers (2024-01-06T08:09:54Z) - Implicit Event-RGBD Neural SLAM [54.74363487009845]
Implicit neural SLAM has achieved remarkable progress recently.
Existing methods face significant challenges in non-ideal scenarios.
We propose EN-SLAM, the first event-RGBD implicit neural SLAM framework.
arXiv Detail & Related papers (2023-11-18T08:48:58Z) - EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields [80.94515892378053]
EvDNeRF is a pipeline for generating event data and training an event-based dynamic NeRF.
NeRFs offer geometric-based learnable rendering, but prior work with events has only considered reconstruction of static scenes.
We show that by training on varied batch sizes of events, we can improve test-time predictions of events at fine time resolutions.
arXiv Detail & Related papers (2023-10-03T21:08:41Z) - Dual Memory Aggregation Network for Event-Based Object Detection with
Learnable Representation [79.02808071245634]
Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner.
Event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation.
Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars.
arXiv Detail & Related papers (2023-03-17T12:12:41Z) - Event Voxel Set Transformer for Spatiotemporal Representation Learning
on Event Streams [23.872611710730865]
Event cameras are neuromorphic vision sensors representing visual information as sparse and asynchronous event streams.
We develop a novel attention-aware model named Event Voxel Set Transformer (EVSTr) for representation learning on event streams.
We evaluate the proposed model on two event-based recognition tasks: object classification and action recognition.
arXiv Detail & Related papers (2023-03-07T12:48:02Z) - Event Data Association via Robust Model Fitting for Event-based Object Tracking [66.05728523166755]
We propose a novel Event Data Association (called EDA) approach to explicitly address the event association and fusion problem.
The proposed EDA seeks for event trajectories that best fit the event data, in order to perform unifying data association and information fusion.
The experimental results show the effectiveness of EDA under challenging scenarios, such as high speed, motion blur, and high dynamic range conditions.
arXiv Detail & Related papers (2021-10-25T13:56:00Z) - Robust Event Classification Using Imperfect Real-world PMU Data [58.26737360525643]
We study robust event classification using imperfect real-world phasor measurement unit (PMU) data.
We develop a novel machine learning framework for training robust event classifiers.
arXiv Detail & Related papers (2021-10-19T17:41:43Z) - EventDrop: data augmentation for event-based learning [0.3670422696827526]
EventDrop is a new method for augmenting asynchronous event data to improve the generalization of deep models.
From a practical perspective, EventDrop is simple to implement and computationally low-cost.
arXiv Detail & Related papers (2021-06-07T11:53:14Z) - Differentiable Event Stream Simulator for Non-Rigid 3D Tracking [82.56690776283428]
Our differentiable simulator enables non-rigid 3D tracking of deformable objects from event streams.
We show the effectiveness of our approach for various types of non-rigid objects and compare to existing methods for non-rigid 3D tracking.
arXiv Detail & Related papers (2021-04-30T17:58:07Z)
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.