Table 3. Detection results for SLNO-S and SLNO on the Foggy Cityscapes test set (from Cityscapes to Foggy Cityscapes).

The best AP of each object category is bold-faced (%).

Approach	Backbone	mAP	person	rider	car	truck	bus	train	mcycle	bicycle
Faster R-CNN(baseline)	VGG-16	22.0	24.4	30.5	32.6	10.8	25.4	9.1	15.2	28.3
DA-Faster [9]	VGG-16	27.6	25.0	31.0	40.5	22.1	35.3	20.2	20.0	27.1
SW-Faster [10]	VGG-16	34.8	32.3	42.2	47.3	23.7	41.3	27.8	28.3	35.4
SC-DA(Type3) [10]	VGG-16	33.8	33.5	38.0	48.5	26.5	39.0	23.3	28	33.6
DT Model [13]	VGG-16	31.5	25.4	39.3	42.4	24.9	40.4	23.1	25.9	30.4
DD-MRL [23]	VGG-16	34.6	30.8	40.5	44.3	27.2	38.4	34.5	28.4	32.2
MTOR [20]	Resnet-50	35.1	30.6	41.4	44.0	21.9	38.6	40.6	28.3	35.6
SLNO-S (ours)	VGG-16	36.1	33.1	43.8	49.2	24.8	42.2	28.9	29.7	36.8
SLNO (λ = 0.17)(ours)	VGG-16	36.3	33.4	44.1	49.3	24.9	42.3	29.3	30.1	37.1