AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

Ziteng Cui, Guo-Jun Qi, Lin Gu, Shaodi You, Zenghui Zhang, Tatsuya Harada

ICCV 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 207 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 orthogonal tangent regularity (ablation)MAET (YOLOv3) · VOC07 test (synthetic low-light)AP50: 0.770 -> 0.788Improved
add orthogonal tangent regularity (ablation)MAET (YOLOv3) · COCO val (synthetic low-light)AP: 0.321 -> 0.330Improved
add orthogonal tangent regularity (ablation)MAET (YOLOv3) · COCO val (synthetic low-light)AP50: 0.534 -> 0.569Improved
add orthogonal tangent regularity (ablation)MAET (YOLOv3) · COCO val (synthetic low-light)AP_S: 0.163 -> 0.189Improved
add orthogonal tangent regularity (ablation)MAET (YOLOv3) · ExDarkmAP: 0.722 -> 0.740Improved
add orthogonal tangent regularity (ablation)MAET (YOLOv3) · UG2+ DARK FACEmAP: 0.542 -> 0.558Improved
add degradation-decoding task (MAET) without ort, versus detector trained on synthetic low-light only (ablation)YOLOv3 · VOC07 test (synthetic low-light)AP50: 0.764 -> 0.770Improved
add degradation-decoding task (MAET) without ort, versus detector trained on synthetic low-light only (ablation)YOLOv3 · ExDarkmAP: 0.716 -> 0.722No clear effect
add degradation-decoding task (MAET) without ort, versus detector trained on synthetic low-light only (ablation)YOLOv3 · UG2+ DARK FACEmAP: 0.540 -> 0.542No clear effect
use our ISP-based synthesis instead of Retinex synthesis (ablation)YOLO (L) · ExDarkmAP: 0.698 -> 0.716Improved
use our ISP-based synthesis instead of Retinex synthesis (ablation)YOLO (L) · UG2+ DARK FACEmAP: 0.511 -> 0.540Improved
use our synthesis instead of inverse gamma with mixed Gaussian-Poisson noise (ablation)YOLO (L) · UG2+ DARK FACEmAP: 0.535 -> 0.540Improved

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