ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification

M. Middleton; H. Kayan; B. Sen Bhattacharya; T. Ali; E. Baikas; M. Vousden; C. Perera; O. Rhodes

cs.NEAug 27, 2026

ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification

Authors: M. Middleton, H. Kayan, B. Sen Bhattacharya, T. Ali, E. Baikas, M. Vousden, C. Perera, O. Rhodes,

Organizations: University of York, UK · Cardiff University, UK · University of Manchester, UK · University of Stirling, UK ·

Abstract

Object classification in event-based computer vision is a task that is attracting considerable research attention. Event-based object classification is a fundamental task in the fields of security and applied computer vision, which typically use synchronous frame-based cameras and computing pipelines for operation. This approach has several practical flaws. The size, weight and power consumption of the device could prohibit deployment at the extreme edge or in covert sensing environments. Besides this, there are security concerns inherent in cloud-based or other off-device computation approaches due to the requirement of sending and receiving potentially sensitive data. Furthermore, this transmission of data introduces latency and requires consistent connectivity to the cloud infrastructure to function. The use of Spiking Neural Networks (SNNs) hosted on neuromorphic devices attempts to solve several issues present in this conventional approach. Research into event-based object classification methods are hindered by the lack of high-quality vision datasets to use. To this end, the ANTShapes simulation tool has been previously proposed to create and label event-based vision datasets. In this paper, four novel datasets of varying difficulties are created using the tool and are benchmarked against existing spiking datasets commonly used for event-based vision research (N-MNIST, CIFAR10-DVS, DVSGesture and POKER-DVS). Classification is performed using a convolutional SNN. This work simultaneously provides four datasets with rich details for future experiments to use and validates the output of the ANTShapes dataset simulation tool as being suitable for its purpose.

Figures & tables

Figure 1: Examples of the 0, 1, 2 and 3 classes taken from the N-MNIST dataset. A denoising process (explained later in Section 4.1 is applied before events are accumulated per-pixel for display. Pixels with more "on" than "off" events are coloured red whilst pixels of the opposite case are coloured blue.

Figure 2: Examples of the "airplane", "cat", "truck" and "horse" classes taken from the CIFAR10-DVS dataset.

Figure 3: Examples of the four classes of poker card symbols taken from the POKER-DVS dataset. The resolution of $35\times 35$ pixels shown here is used in practice for POKER-DVS rather than the published value of $32\times 32$ . Some Python implementations of the dataset, such as the Tonic package implementation, use a resolution of $35\times 35$ pixels.

Figure 4: Examples of the "hand clapping", "right arm CW", "left arm CW" and "arm roll" classes taken from the DVSGesture dataset. The right and left arm gestures represent moving the relevant arm in a circular motion clockwise.

Dataset	Purpose	Spatial Resolution	Num. Classes	Type of Features	Contains DVS Noise?
N-MNIST	Handwritten digit classification	$34\times 34$	10	Saccadic eye mimic	Yes
CIFAR10-DVS	Image classification	$128\times 128$	10	Saccadic eye mimic	Yes
POKER-DVS	Object detail classification	$32\times 32$	4	Natural scene	Yes
DVSGesture	Object detail classification	$128\times 128$	10 + 1 “other”	Natural scene	Yes

Table 1: Overview of the four existing datasets discussed here. Only one dataset, CIFAR10-DVS, is specifically targeted towards the classification of an entire object rather than just details expressed on or by an object (such as suit printed on a card or gesture expressed by a person’s body).

Parameter	Setting	Description
Initial Rotation $\sigma$ , $(x,y,z)$	180	Randomises the initial rotation position of the object around the $(x,y,z)$ axes.
Initial Position $\sigma$ $(x,y)$	0.15	Displaces the shape from the center of the scene on the horizontal and vertical axes. This provides variance in the dataset by randomising object positions within scenes over each example.
Scale $\mu$ $(x,y,z)$	4	A constant scaling value is applied to all shapes to enlarge them in the scene. Scaling is applied uniformly across the $(x,y,z)$ axes.
Surface Noise $\mu$	0.2	Applies normal-mapped noise to the surfaces of objects. This applies visual texture to shapes which is dependent on the incident angle of the scene light source.
Anomaly Labelling	Disabled	All anomaly labelling supported by ANTShapes is disabled as it is not relevant to the object classification task.

Table 2: Configuration used to generate the standard ANTShapes dataset in the simulation program. These configurations are applied globally to all classes of objects. ANTShapes parameters are defined as normal distributions and accept values for the mean

\mu

and variance

\sigma

. Per-shape parameters are sampled from these defined distributions, causing each example rendered for the dataset to be unique.

Figure 5: Examples of four classes taken from the "standard" ANTShapes dataset. As in Figures 1 to 4 , the events pictured are accumulated over the simulation period leading to the "smearing" effect seen. Variance in the positioning of the objects is seen between examples, as each appears in a different location in the scene. The simulated data is also free from background noise.

Figure 6: Examples from the ANTShapes "translation" dataset. Compared to the standard dataset shown in Figure 5 , it can be seen that the shapes move with different trajectories and rebound from the edges of the simulated scene whilst rotating.

Figure 7: Four classes taken from the "distortion" dataset. These objects each have 3 randomly-assigned scaling vectors which are each applied to the $X$ , $Y$ and $Z$ dimensions to distort the object’s event signature.

Figure 8: Four examples from the "rotation" dataset. Unlike the standard dataset, where each object is assigned a random initial rotation then continues to rotate around the $X$ , $Y$ and $Z$ axes uniformly, each simulated object is assigned a random 3D rotation vector. This introduces additional variance between event signatures within classes by introducing independent rotational behaviour for all shapes between examples.

Figure 9: A diagram of the spiking convolutional network design used for the following benchmarking experiments. Here,

T

is the total number of time steps in the dataset where the time between frames is 1ms.

X

and

Y

are the sensor dimensions in pixels; for ANTShapes datasets, this is the spatial resolution of the simulated scene.

C

is the number of classes in the dataset being evaluated and

B

is the batch size. The network architecture pools the features from previous layers, learning the most relevant features through surrogate gradient training. The readout head is trained on the flattened features from the output of the final hidden layer using the cross-entropy loss function. The stage 2 and 3 layers are optional and are only created if the length of the shortest spatial dimension

P_{n}

is greater than 4 pixels.

	N-MNIST	CIFAR10-DVS	POKER-DVS	DVSGesture	ANTShapes (Standard)	ANTShapes (Translation)	ANTShapes (Distortion)	ANTShapes (Rotation)
Mean Accuracy	97%	55.6%	96.6%	88.9%	92.2%	89.1%	83.5%	89.8%
Variance	$2.8\times 10^{-3}$	$5.3\times 10^{-3}$	$11.0\times 10^{-3}$	$12.0\times 10^{-3}$	$12.0\times 10^{-3}$	$8.6\times 10^{-3}$	$16.0\times 10^{-3}$	$7.8\times 10^{-3}$

Table 3: Summary of the mean accuracy and variance for all datasets. 10 convolutional SNNs, each with unique random initial weights, were trained. The mean accuracy and variance of the ensembles are shown.

Figure 10: Confusion matrices produced for each dataset, illustrating the class confusions predicted by the convolutional SNN. The mean over all 10 trials is plotted here to give an impression of the average confusion matrix produced by the network for a given dataset.

Figure 11: PCA plots created for each of the datasets evaluated in this paper. The DVSGesture plots show clear separation, but also class overlap between clockwise (CW) and counter-clockwise (CCW) motion, which leads to difficulties in separating the classes. POKER-DVS shows clear separation, but only contains 4 classes and a limited number of samples. CIFAR10-DVS shows extreme overlap of principal elements for all classes, demonstrating that the principal components for each class are largely similar and are difficult to separate. The standard ANTShapes dataset has clear separation between most classes, with some overlap between the L-block and T-block objects, and between the various smooth-faced objects (such as cones and capsules). The separation between principal component clusters becomes less well-defined when random rotation, translation and scaling (distortion) vectors are introduced to the objects presented in each example. For all ANTShapes datasets, the sphere objects remain the most cleanly separated from the rest of the classes. This is due to their near-uniform appearance when rotated, with events only being generated from the motion of simulated roughness on the sphere’s surface. Their event signature is therefore distinct from the other objects presented, which can appear different depending on their angle of rotation.

Event-Based Vision

Event-based vision uses asynchronous camera measurements to perceive motion and scene changes with high temporal resolution and dynamic range.

See all 227 papers

Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision
Feb 26, 2026Mike Middleton, Teymoor Ali, Hakan Kayan +6Synthetic Anomaly Generation Event-Based Vision
Bio-Inspired Systems and Technologies Lab, University of York, York, UK · Faculty of Natural Sciences, University of Stirling, Stirling, UK · School of Computer Science and Informatics, Cardiff University, Cardiff, UK +2
Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark
Apr 30, 2026Udayanga G. W. K. N. Gamage, Yan Zeng, Cesar Cadena +2Edge Inference Spiking Neural Networks
Department of Electrical and Photonics Engineering, Technical University of Denmark, Anker Engelunds Vej 1, 2800 Kongens Lyngby, Denmark · Faculty of Engineering, University of Ruhuna, Hapugala,Galle 80000, Sri Lanka · Autonomous Systems Lab, ETH zürich, Leonhardstrasse 21, 8092 Zürich, Switzerland
SpikeCLR: Contrastive Self-Supervised Learning for Few-Shot Event-Based Vision using Spiking Neural Networks
Mar 17, 2026Maxime Vaillant, Axel Carlier, Lai Xing Ng +2Self-Supervised Visual Representation Learning Event-Based Vision
CNRS, IPAL IRL 2955, Singapore · Université de Toulouse, IRIT, France · Institute for Infocomm Research, A*STAR, Singapore +2

Feb 26, 2026J/K move · Enter open · S save

Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision

Mike Middleton, Teymoor Ali, Hakan Kayan, Basabdatta Sen Bhattacharya+5

Bio-Inspired Systems and Technologies Lab, University of York, York, UK · Faculty of Natural Sciences, University of Stirling, Stirling, UK · School of Computer Science and Informatics, Cardiff University, Cardiff, UK+2

Synthetic Anomaly Generation Event-Based Vision Neuromorphic Computing Anomaly Detection

Open paper AskPDF arXiv

Limitations on the availability of Dynamic Vision Sensors (DVS) present a fundamental challenge to researchers of neuromorphic computer vision applications. In response, datasets have been created by the research community, but often contain a limited number of samples or scenarios. To address the lack of a comprehensive simulator of neuromorphic vision datasets, we introduce the Anomalous Neuromorphic Tool for Shapes (ANTShapes), a novel dataset simulation framework. Built in the Unity engine, ANTShapes simulates abstract, configurable 3D scenes populated by objects displaying randomly-generated behaviours describing attributes such as motion and rotation. The sampling of object behaviours, and the labelling of anomalously-acting objects, is a statistical process following central limit theorem principles. Datasets containing an arbitrary number of samples can be created and exported from ANTShapes, along with accompanying label and frame data, through the adjustment of a limited number of parameters within the software. ANTShapes addresses the limitations of data availability to researchers of event-based computer vision by allowing for the simulation of bespoke datasets to suit purposes including object recognition and localisation alongside anomaly detection.

Abstract

Event-Based Vision

Explore similar work

Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision

Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark

SpikeCLR: Contrastive Self-Supervised Learning for Few-Shot Event-Based Vision using Spiking Neural Networks