Pedestrian Detection On Llvip

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	AP	Paper Title	Repository
CMX	0.596	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
CFT	0.636	Cross-Modality Fusion Transformer for Multispectral Object Detection
MMPedestron	0.726	When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset
CSSA	0.592	Multimodal Object Detection by Channel Switching and Spatial Attention	-
GAFF	0.558	Multimodal Object Detection by Channel Switching and Spatial Attention	-
Halfway Fusion	0.551	Multimodal Object Detection by Channel Switching and Spatial Attention	-
ProbEn	0.515	Multimodal Object Detection via Probabilistic Ensembling
UniRGB-IR	0.632	UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning
ProbEn	0.515	Multimodal Object Detection by Channel Switching and Spatial Attention	-
INSANet	-	INSANet: INtra-INter Spectral Attention Network for Effective Feature Fusion of Multispectral Pedestrian Detection
YoloV5-RGB	0.527	LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
MiPa	0.665	MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection
YoloV3-RGB	0.466	LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
RSDet	0.613	Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection

0 of 14 row(s) selected.