Summary of Eas-snn: End-to-end Adaptive Sampling and Representation For Event-based Detection with Recurrent Spiking Neural Networks, by Ziming Wang et al.
EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks
by Ziming Wang, Ziling Wang, Huaning Li, Lang Qin, Runhao Jiang, De Ma, Huajin Tang
First submitted to arxiv on: 19 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed event-based detection framework leverages Spiking Neural Networks (SNNs) to address the crucial issue of adaptive event sampling in object detection. The study discovers that SNN neural dynamics align with ideal temporal event sampling behavior, motivating a novel adaptive sampling module that integrates recurrent convolutional SNNs with temporal memory for end-to-end learnability. Additionally, Residual Potential Dropout (RPD) and Spike-Aware Training (SAT) are introduced to regulate potential distribution and address performance degradation. The framework outperforms existing state-of-the-art spike-based methods with fewer parameters and time steps, achieving a 4.4% mAP improvement on the Gen1 dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new approach for event-based object detection using Spiking Neural Networks (SNNs). It shows that SNNs can be used to adaptively sample events in order to improve detection performance. The method is compared to existing state-of-the-art methods and is shown to perform better with fewer parameters and time steps. |
Keywords
» Artificial intelligence » Dropout » Object detection
