Papers › N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras

N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras

2 Dec 2021ICCV 2021 10arXiv:2112.01041archive 2025-07-28

Junho Kim, Jaehyeok Bae, Gangin Park, Dongsu Zhang, Young Min Kim

We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras. The dataset is collected using programmable hardware in which an event camera consistently moves around a monitor displaying images from ImageNet. N-ImageNet serves as a challenging benchmark for event-based object recognition, due to its large number of classes and samples. We empirically show that pretraining on N-ImageNet improves the performance of event-based classifiers and helps them learn with few labeled data. In addition, we present several variants of N-ImageNet to test the robustness of event-based classifiers under diverse camera trajectories and severe lighting conditions, and propose a novel event representation to alleviate the performance degradation. To the best of our knowledge, we are the first to quantitatively investigate the consequences caused by various environmental conditions on event-based object recognition algorithms. N-ImageNet and its variants are expected to guide practical implementations for deploying event-based object recognition algorithms in the real world.

Paper PDF Conference PDF Code

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

Code

82magnolia/n_imagenet officialmentioned in paperpytorchGPL-3.0 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification Object Object Recognition Robust classification

Datasets

Introduced by this paper, per the archive.

N-ImageNet

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Classification	N-ImageNet	Event Spike Tensor	Accuracy (%)	48.93	#1 of 9	Archive leaderboard	report
Classification	N-ImageNet	DiST	Accuracy (%)	48.43	#2 of 9	Archive leaderboard	report
Classification	N-ImageNet	Sorted Time Surface	Accuracy (%)	47.90	#3 of 9	Archive leaderboard	report
Classification	N-ImageNet	Event Histogram	Accuracy (%)	47.73	#4 of 9	Archive leaderboard	report
Classification	N-ImageNet	HATS	Accuracy (%)	47.14	#5 of 9	Archive leaderboard	report
Classification	N-ImageNet	Binary Event Image	Accuracy (%)	46.36	#6 of 9	Archive leaderboard	report
Classification	N-ImageNet	Timestamp Image	Accuracy (%)	45.86	#7 of 9	Archive leaderboard	report
Classification	N-ImageNet	Event Image	Accuracy (%)	45.77	#8 of 9	Archive leaderboard	report
Classification	N-ImageNet	Time Surface	Accuracy (%)	44.32	#9 of 9	Archive leaderboard	report
Classification	N-ImageNet (mini)	Event Imge	Accuracy (%)	61.42	#1 of 6	Archive leaderboard	report
Classification	N-ImageNet (mini)	Event Histogram	Accuracy (%)	61.02	#2 of 6	Archive leaderboard	report
Classification	N-ImageNet (mini)	Timestamp Image	Accuracy (%)	60.46	#3 of 6	Archive leaderboard	report
Classification	N-ImageNet (mini)	DiST	Accuracy (%)	59.74	#4 of 6	Archive leaderboard	report
Classification	N-ImageNet (mini)	Sorted Time Surface	Accuracy (%)	58.38	#5 of 6	Archive leaderboard	report
Classification	N-ImageNet (mini)	Binary Event Image	Accuracy (%)	53.52	#6 of 6	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.

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