Table 1.

Classification results (accuracy %) on Office-31 dataset with ResNet-50 as the backbone. ↑ denotes an increase in performance. The bold number indicates the best performance.

Methods	A→W	D→W	W→D	A→D	D→A	W→A	Avg
ResNet50	68.4 ± 0.2	96.7 ± 0.1	99.3 ± 0.1	68.9 ± 0.2	62.5 ± 0.3	60.7 ± 0.3	76.1
ADDA	86.2 ± 0.5	96.2 ± 0.3	98.4 ± 0.3	77.8 ± 0.3	69.5 ± 0.4	68.9 ± 0.5	82.9
MADA	90.1 ± 0.1	97.4 ± 0.1	99.6 ± 0.1	87.8 ± 0.2	70.3 ± 0.3	66.4 ± 0.3	85.2
MDD	94.5 ± 0.3	98.4 ± 0.1	100.0 ± 0.0	93.5 ± 0.2	74.6 ± 0.3	72.2 ± 0.1	88.9
BSP	93.3 ± 0.2	98.2 ± 0.2	100.0 ± 0.0	93.0 ± 0.2	73.6 ± 0.3	72.6 ± 0.3	88.5
BNM	92.8 ± 0.1	98.8 ± 0.1	100.0 ± 0.0	92.9 ± 0.2	73.5 ± 0.2	73.8 ± 0.3	88.6
ALDA	95.6 ± 0.5	97.7 ± 0.1	100 ± 0.0	94.0 ± 0.4	72.2 ± 0.4	72.5 ± 0.2	88.9
GVB-GD	94.8 ± 0.5	98.7 ± 0.3	100.0 ± 0.0	95.0 ± 0.4	73.4 ± 0.3	73.7 ± 0.4	89.3
f-DAL	95.4 ± 0.7	98.8 ± 0.1	100.0 ± 0.0	93.8 ± 0.4	74.9 ± 1.5	74.2 ± 0.5	89.5
GVB+MetaAlign	93.0 ± 0.5	98.6 ± 0.0	100.0 ± 0.0	94.5 ± 0.3	75.0 ± 0.3	73.6 ± 0.0	89.2
DWL	89.2	99.2	100.0	91.2	73.1	69.8	87.1
DANN	82.0 ± 0.4	96.9 ± 0.2	99.1 ± 0.1	79.7 ± 0.4	68.2 ± 0.4	67.4 ± 0.5	82.2
DANN+MRE	91.9 ± 0.6 ↑	98.6 ± 0.0 ↑	99.3 ± 0.1 ↑	88.6 ± 0.2 ↑	71.7 ± 0.3 ↑	72.1 ± 0.3 ↑	87.0 ↑
CDAN	93.1 ± 0.1	98.6 ± 0.1	100.0 ± 0.0	92.9 ± 0.2	71.0 ± 0.3	70.3 ± 0.3	87.7
CDAN+MRE	94.3 ± 0.4 ↑	98.6 ± 0.2	100.0 ± 0.0	95.5 ± 0.2 ↑	75.8 ± 0.4 ↑	74.6 ± 0.4 ↑	89.8 ↑