Table 3.

Classification results (accuracy %) of different methods on Office-Home dataset. The backbone network is ResNet-50. ↑ denotes an increase in performance. The bold number indicates the best performance.

Methods	Ar→Cl	Ar→Pr	Ar→Rw	Cl→Ar	Cl→Pr	Cl→Rw	Pr→Ar	Pr→Cl	Pr→Rw	Rw→Ar	Rw→Cl	Rw→Pr	Avg
ResNet50	34.9	50.0	58.0	37.4	41.9	46.2	38.5	31.2	60.4	53.9	41.2	59.9	46.1
DAN	43.6	57.0	67.9	45.8	56.5	60.4	44.0	43.6	67.7	63.1	51.5	74.3	56.3
JAN	45.9	61.2	68.9	50.4	59.7	61.0	45.8	43.4	70.3	63.9	52.4	76.8	58.3
MDD	54.9	73.7	77.8	60.0	71.4	71.8	61.2	53.6	78.1	72.5	60.2	82.3	68.1
BSP	52.0	68.6	76.1	58.0	70.3	70.2	58.6	50.2	77.6	72.2	59.3	81.9	66.3
ALDA	53.7	70.1	76.4	60.2	72.6	71.5	56.8	51.9	77.1	70.2	56.3	82.1	66.6
BNM	56.2	73.7	79.0	63.1	73.6	74.0	62.4	54.8	80.7	72.4	58.9	83.5	69.4
MDD+Implicit	56.2	77.9	79.2	64.4	73.1	74.4	64.2	54.2	79.9	71.2	58.1	83.1	69.5
GVB-GD	57.0	74.7	79.8	64.6	74.1	74.6	65.2	55.1	81.0	74.6	59.7	84.3	70.4
f-DAL	54.7	71.7	77.8	61.0	72.6	72.2	60.8	53.4	80.0	73.3	60.6	83.8	68.5
JUMBOT	55.2	75.5	80.8	65.5	74.4	74.9	65.2	52.7	79.2	73.0	59.9	83.4	70.0
DANN+MetaAlign	48.6	69.5	76.0	58.1	65.7	68.3	54.9	44.4	75.3	68.5	50.8	80.1	63.3
CDAN+MetaAlign	55.2	70.5	77.6	61.5	70.0	70.0	58.7	55.7	78.5	73.3	61.0	81.7	67.8
DANN	45.6	59.3	70.1	47.0	58.5	60.9	46.1	43.7	68.5	63.2	51.8	76.8	57.6
DANN+MRE	52.8 ↑	69.7 ↑	76.3 ↑	58.7 ↑	70.9 ↑	70.8 ↑	58.6 ↑	51.8 ↑	78.6 ↑	70.6 ↑	57.3 ↑	82.7 ↑	66.6 ↑
CDAN	50.8	68.3	74.9	58.4	70.6	70.1	54.8	48.7	76.6	70.3	57.7	81.6	65.2
CDAN+MRE	57.8 ↑	75.2 ↑	79.5 ↑	65.9 ↑	74.8 ↑	75.0 ↑	66.8 ↑	56.6 ↑	80.8 ↑	75.8 ↑	60.2 ↑	84.3 ↑	71.1 ↑