SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09274 · ICLR · 2024

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

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

arXiv · PDF · Open in the Atlas

Code that ran

5 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 11 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.09274.json · badge: /api/ran/2403.09274.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
myuansun/EventRPG canonical (classifier label)
classifier basis: census
3 ran · 7 no recorded run
myuansun/eventrpg canonical (classifier label)
classifier basis: classifier_2025
2 ran · 4 no recorded run
FunctionStatusWhere it lives
TET_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
myuansun/EventRPG/snn_utils/functions.py
code served (permissive licence) · get_code("127b8f6110c5249c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# For mode='TB', outputs shape should be (T, B, num_classes)
# T is time steps, B is batch size, num_classes is number of classes
T = 3
B = 2
num_classes = 4

# Create outputs tensor with shape (T, B, num_classes) for mode='TB'
outputs = torch.randn(T, B, num_classes)

# Create labels tensor with shape (B,) containing class indices
labels = torch.randint(0, num_classes, (B,))

# Create criterion
criterion = torch.nn.CrossEntropyLoss()

# Set means and lamb parameters
means = 1.0
lamb = 0.001

# Set mode
mode = 'TB'

ARGS = {
    'outputs': outputs,
    'labels': labels,
    'criterion': criterion,
    'means': means,
    'lamb': lamb,
    'mode': mode
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mid_normalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
myuansun/eventrpg/utils/RelCAM.py
code served (permissive licence) · get_code("530a364d830eeefc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 5, dtype family float, shape (2, 3, 4, 5, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small test tensor with shape (B, C, T, H, W) = (2, 3, 4, 5, 6)
# This will be reshaped to (B, T, C, H, W) = (2, 4, 3, 5, 6) inside the function
representation = torch.randn(2, 3, 4, 5, 6)

ARGS = {
    "representation": representation
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 5, dtype family float, shape (2, 3, 4, 5, 6) — shape (2, 3, 4, 5, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mixup_criterion_raw_events Ran
ran; our contract draft was wrong, not the code
myuansun/EventRPG/train_distributed.py
code served (permissive licence) · get_code("e22727da062c7d52")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create pred tensor: batch_size=2, num_classes=4
pred = torch.randn(2, 4)

# Create target tensor: batch_size=2, with columns [class1, class2, sigma]
target = torch.tensor([
    [0, 1, 0.7],
    [2, 3, 0.3]
], dtype=torch.float32)

# Create cross_entropy_loss function
cross_entropy_loss = nn.CrossEntropyLoss()

ARGS = {
    "pred": pred,
    "target": target,
    "cross_entropy_loss": cross_entropy_loss
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
percentile Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
myuansun/eventrpg/utils/RelCAM.py
code served (permissive licence) · get_code("1b03542f209fada4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 5, dtype family float, shape (2, 3, 4, 1, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a tensor with shape (B, C, T, H, W)
# Using distinct sizes: B=2, C=3, T=4, H=5, W=6
t = torch.randn(2, 3, 4, 5, 6)

# q is a percentile value (0-100)
q = 50

ARGS = {
    "t": t,
    "q": q,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 5, dtype family float, shape (2, 3, 4, 1, 1) — shape (2, 3, 4, 1, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
safe_divide Ran
ran, honoured the contract we drafted
myuansun/EventRPG/snn_utils/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from wjNam/Relative_Attributing_Propagation, is pointer only (licence: NONE) · get_code("251e368f5f9b12f5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from wjNam/Relative_Attributing_Propagation, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RelProp Not yet run
unverified (harvested, no recorded run)
myuansun/eventrpg/snn_utils/layers.py
code served (permissive licence) · get_code("67cfeaf9efec718e")
How it ran

no invocation recorded.

conv1x1 Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/snn_utils/sew_resnet.py
code served (permissive licence) · get_code("747f3bb47629c67a")
How it ran

no invocation recorded.

conv1x1 Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/utils/resnet.py
code served (permissive licence) · get_code("19a22f01cee3edae")
How it ran

no invocation recorded.

conv3x3 Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/snn_utils/sew_resnet.py
code served (permissive licence) · get_code("e9e146fe9b081dfa")
How it ran

no invocation recorded.

conv3x3 Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/utils/resnet.py
code served (permissive licence) · get_code("c930c4c4b347fdeb")
How it ran

no invocation recorded.

mixup_criterion_raw_events Not yet run
unverified (harvested, no recorded run)
myuansun/eventrpg/snn_train.py
code served (permissive licence) · get_code("981e67821bf26084")
How it ran

no invocation recorded.

reduce_mean Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/snn_train_distributed.py
code served (permissive licence) · get_code("f4154dada5bcd3af")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/utils/resnet.py
code served (permissive licence) · get_code("f15b5608e35440eb")
How it ran

no invocation recorded.

sew_function Not yet run
unverified (harvested, no recorded run)
myuansun/EventRPG/snn_utils/sew_resnet.py
code served (permissive licence) · get_code("4682daea820db90c")
How it ran

no invocation recorded.

slrp_forward_hook Not yet run
unverified (harvested, no recorded run)
myuansun/eventrpg/snn_utils/layers.py
code served (permissive licence) · get_code("19e247af0b21c75a")
How it ran

no invocation recorded.

sltrp_forward_hook Not yet run
unverified (harvested, no recorded run)
myuansun/eventrpg/snn_utils/layers.py
code served (permissive licence) · get_code("171f1ac017872454")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 3 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
resnet18 89 other papers
76 dated earlier, 1 the same month, 10 later, 2 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
conv3x3 9 other papers
5 dated earlier, 3 later, 1 same year, order not determinable
2001.06838 (2020-01)
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
2004.00288 (2020-04)
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
2107.08621 (2021-07)
Face.evoLVe: A High-Performance Face Recognition Library
and 6 more not named here
conv1x1 8 other papers
6 dated earlier, 2 later
2001.06838 (2020-01)
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
2004.00288 (2020-04)
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
2008.04115 (2020-08)
T-GD: Transferable GAN-generated Images Detection Framework
and 5 more not named here
safe_divide 3 other papers
3 dated earlier
1904.00605 (2019-04)
Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks
2310.04519 (2023-10)
SPADE: Sparsity-Guided Debugging for Deep Neural Networks
2402.03348 (2024-02)
Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 saliencybased 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.09274")
get_code_for_paper("2403.09274")
have("2403.09274")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.09274.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.09274.svg)](https://syntology.ai/paper/2403.09274)

Connect an agent — have() is free.