Papers › EventRPG: Event Data Augmentation with Relevance Propagation Guidance

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

14 Mar 2024arXiv:2403.09274archive 2025-07-28

Mingyuan Sun, Donghao Zhang, ZongYuan Ge, Jiaxu Wang, Jia Li, Zheng Fang, Renjing Xu

Event camera, a novel bio-inspired vision sensor, has drawn a lot of attention for its low latency, low power consumption, and high dynamic range. Currently, overfitting remains a critical problem in event-based classification tasks for Spiking Neural Network (SNN) due to its relatively weak spatial representation capability. Data augmentation is a simple but efficient method to alleviate overfitting and improve the generalization ability of neural networks, and saliency-based augmentation methods are proven to be effective in the image processing field. However, there is no approach available for extracting saliency maps from SNNs. Therefore, for the first time, we present Spiking Layer-Time-wise Relevance Propagation rule (SLTRP) and Spiking Layer-wise Relevance Propagation rule (SLRP) in order for SNN to generate stable and accurate CAMs and saliency maps. Based on this, we propose EventRPG, which leverages relevance propagation on the spiking neural network for more efficient augmentation. Our proposed method has been evaluated on several SNN structures, achieving state-of-the-art performance in object recognition tasks including N-Caltech101, CIFAR10-DVS, with accuracies of 85.62% and 85.55%, as well as action recognition task SL-Animals with an accuracy of 91.59%. Our code is available at https://github.com/myuansun/EventRPG.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2403.09274")

Code

Syntology Ran 5 of 16 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

myuansun/eventrpg officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 5 ran; 1 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · fixture could not drive it
2ran
11unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from myuansun/EventRPG. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

TET_loss myuansun/EventRPG/snn_utils/functions.py official repository ran MIT (permissive) · 127b8f6110c5249c · report
mid_normalize myuansun/eventrpg/utils/RelCAM.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 530a364d830eeefc · report
mixup_criterion_raw_events myuansun/EventRPG/train_distributed.py official repository ran MIT (permissive) · e22727da062c7d52 · report
percentile myuansun/eventrpg/utils/RelCAM.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 1b03542f209fada4 · report
safe_divide myuansun/EventRPG/snn_utils/layers.py official repository ran · honoured contract fingerprinted MIT (permissive) · 251e368f5f9b12f5 · report
RelProp myuansun/eventrpg/snn_utils/layers.py official repository unverified MIT (permissive) · 67cfeaf9efec718e · report
conv1x1 myuansun/EventRPG/snn_utils/sew_resnet.py official repository unverified MIT (permissive) · 747f3bb47629c67a · report
conv1x1 myuansun/EventRPG/utils/resnet.py official repository unverified MIT (permissive) · 19a22f01cee3edae · report
conv3x3 myuansun/EventRPG/snn_utils/sew_resnet.py official repository unverified MIT (permissive) · e9e146fe9b081dfa · report
conv3x3 myuansun/EventRPG/utils/resnet.py official repository unverified MIT (permissive) · c930c4c4b347fdeb · report
mixup_criterion_raw_events myuansun/eventrpg/snn_train.py official repository unverified MIT (permissive) · 981e67821bf26084 · report
reduce_mean myuansun/EventRPG/snn_train_distributed.py official repository unverified MIT (permissive) · f4154dada5bcd3af · report
resnet18 myuansun/EventRPG/utils/resnet.py official repository unverified MIT (permissive) · f15b5608e35440eb · report
sew_function myuansun/EventRPG/snn_utils/sew_resnet.py official repository unverified MIT (permissive) · 4682daea820db90c · report
slrp_forward_hook myuansun/eventrpg/snn_utils/layers.py official repository unverified MIT (permissive) · 19e247af0b21c75a · report
sltrp_forward_hook myuansun/eventrpg/snn_utils/layers.py official repository unverified MIT (permissive) · 171f1ac017872454 · report

Tasks

Action RecognitionData AugmentationObject Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition DVS128 Gesture SEW-Resnet18 Accuracy (% ) 96.53 #1 of 1 Archive leaderboard report
Action Recognition SL-Animals SEW-Resnet18 (3sets) Accuracy (% ) 93.75 #1 of 2 Archive leaderboard report
Action Recognition SL-Animals SEW-Resnet18 (4sets) Accuracy (% ) 91.59 #2 of 2 Archive leaderboard report
Object Recognition CIFAR10-DVS Spike-VGG11 Accuracy (% ) 85.55 #1 of 2 Archive leaderboard report
Object Recognition N-CARS Spike-VGG11 Accuracy (% ) 96.00 #1 of 1 Archive leaderboard report
Object Recognition N-Caltech 101 Spike-VGG11 Accuracy (% ) 85.62 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SNN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections