Table 8 Ablation study results on the Foggy Cityspaces dataset.

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

Module

V0

V1

V2

V3

V4

V5

Baseline

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

DFN

 

\(\checkmark\)

 

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

MCA

  

\(\checkmark\)

 

\(\checkmark\)

\(\checkmark\)

HPAT

  

\(\checkmark\)

\(\checkmark\)

 

\(\checkmark\)

mAP(%)

32.4

34.1

34.9

35.9

36.4

37.8