AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

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

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

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 108 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add sorting to DiT (discounted timestamp image) (ablation)DiST · N-ImageNet valaccuracy: 46.1 -> 48.43Improved
add discounting to sorted time surface (ablation)DiST · N-ImageNet valaccuracy: 47.90 -> 48.43Improved
add sorting to DiT (ablation)DiST · N-ImageNet variants (big trajectory change)accuracy: 33.61 -> 35.85Improved
add discounting to sorted time surface (ablation)DiST · N-ImageNet variants (big brightness change)accuracy: 28.38 -> 30.88Improved
add sorting to DiT (ablation)DiST · N-ImageNet variants (big brightness change)accuracy: 28.42 -> 30.88Improved
pretrain on N-ImageNet instead of random initializationResNet34 event classifiers · N-Caltech101accuracy: 68.12 -> 86.81Improved
pretrain on N-ImageNet instead of ImageNetResNet34 event classifiers · N-Caltech101accuracy: 80.88 -> 86.81Improved
pretrain on N-ImageNet instead of random initializationResNet34 event classifiers · ASL-DVS (800 training samples)accuracy: 29.57 -> 58.28Improved
pretrain on N-ImageNet instead of random initializationResNet34 event classifiers · N-Carsaccuracy: 90.80 -> 94.73Improved
pretrain on N-ImageNet instead of random initializationResNet34 event classifiers · CIFAR10-DVSaccuracy: 62.57 -> 73.72Improved
use relative (sorted) timestamps instead of raw timestampsTimestamp Image · N-ImageNet valaccuracy: 45.86 -> 47.90Improved
use event counts without timestamps instead of raw timestampsEvent Histogram · N-ImageNet valaccuracy: 45.86 -> 47.73Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy