Table 7 Performance evaluation for each object class on KITTI.

From: DSNet enables feature fusion and detail restoration for accurate object detection in foggy conditions

Method

Person

Bicycle

Car

Truck

mAP(%)

YOLOv8

0.854

0.943

0.98

0.991

94.2

AODNet

0.853

0.94

0.979

0.987

94

FFANet

0.851

0.924

0.981

0.99

93.7

CPAEnhancer

0.86

0.938

0.978

0.988

94.1

CDNet

0.843

0.942

0.978

0.989

93.8

CF-YOLO

0.88

0.925

0.977

0.989

94.3

DR-YOLO

0.819

0.904

0.966

0.987

91.9

RDMNet

0.71

0.83

0.96

0.98

87.1

TogetherNet

0.68

0.85

0.95

0.968

86.2

Ours

0.865

0.938

0.983

0.991

94.4

  1. Bold indicates the best performance.
Back to article page