EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision
- URL: http://arxiv.org/abs/2405.18880v1
- Date: Wed, 29 May 2024 08:39:31 GMT
- Title: EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision
- Authors: Yiting Dong, Xiang He, Guobin Shen, Dongcheng Zhao, Yang Li, Yi Zeng,
- Abstract summary: 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.
- Score: 9.447299017563841
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Event data captured by Dynamic Vision Sensors (DVS) offers a unique approach to visual processing that differs from traditional video capture, 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. To address this, we developed EventZoom -- a data augmentation strategy specifically designed for event data. EventZoom employs a progressive temporal strategy that intelligently blends time and space to enhance the diversity and complexity of the data while maintaining its authenticity. This method aims to improve the quality of data for model training and enhance the adaptability and robustness of algorithms in handling complex dynamic scenes. We have experimentally validated EventZoom across various supervised learning frameworks, including supervised, semi-supervised, and unsupervised learning. Our results demonstrate that EventZoom consistently outperforms other data augmentation methods, confirming its effectiveness and applicability as a powerful event-based data augmentation tool in diverse learning settings.
Related papers
- 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) - Leveraging the Power of Data Augmentation for Transformer-based Tracking [64.46371987827312]
We propose two data augmentation methods customized for tracking.
First, we optimize existing random cropping via a dynamic search radius mechanism and simulation for boundary samples.
Second, we propose a token-level feature mixing augmentation strategy, which enables the model against challenges like background interference.
arXiv Detail & Related papers (2023-09-15T09:18:54Z) - Multi-dataset Training of Transformers for Robust Action Recognition [75.5695991766902]
We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition.
Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss.
We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2.
arXiv Detail & Related papers (2022-09-26T01:30:43Z) - Improved Regularization of Event-based Learning by Reversing and
Drifting [4.736525128377909]
Event camera has enormous potential in challenging scenes for its advantages of high temporal resolution, high dynamic range, low power consumption, and no motion blur.
We propose two novel augmentation methods: EventReverse and EventDrift.
arXiv Detail & Related papers (2022-07-24T04:23:56Z) - EventMix: An Efficient Augmentation Strategy for Event-Based Data [4.8416725611508244]
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.
arXiv Detail & Related papers (2022-05-24T13:07:33Z) - Improved Speech Emotion Recognition using Transfer Learning and
Spectrogram Augmentation [56.264157127549446]
Speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction.
One of the main challenges in SER is data scarcity.
We propose a transfer learning strategy combined with spectrogram augmentation.
arXiv Detail & Related papers (2021-08-05T10:39:39Z) - Event-LSTM: An Unsupervised and Asynchronous Learning-based
Representation for Event-based Data [8.931153235278831]
Event cameras are activity-driven bio-inspired vision sensors.
We propose Event-LSTM, an unsupervised Auto-Encoder architecture made up of LSTM layers.
We also push state-of-the-art event de-noising forward by introducing memory into the de-noising process.
arXiv Detail & Related papers (2021-05-10T09:18:52Z) - Learning to Continuously Optimize Wireless Resource in a Dynamic
Environment: A Bilevel Optimization Perspective [52.497514255040514]
This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment.
We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes.
Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2021-05-03T07:23:39Z) - Learning Representational Invariances for Data-Efficient Action
Recognition [52.23716087656834]
We show that our data augmentation strategy leads to promising performance on the Kinetics-100, UCF-101, and HMDB-51 datasets.
We also validate our data augmentation strategy in the fully supervised setting and demonstrate improved performance.
arXiv Detail & Related papers (2021-03-30T17:59:49Z)
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.