Instance-Wise Denoising Autoencoder for High Dimensional Data

Table 6

Transfer learning results on Amazon dataset: comparison results in terms of testing accuracy (%).

Task	SVM-SC	CL-KCCA	HeMap	Msda-CCA	HHTL (1 layer)	HHTL (3 layers)	Ours (1 layer)	Ours (3 layers)
EN-B-FR-D	73.25	50.00	49.45	72.96	72.65	76.75	76.2	78.95
EN-B-FR-M	62.40	47.20	50.70	64.29	63.30	67.65	70.1	70.1
EN-B-GE-D	72.55	77.50	66.12	78.23	70.95	75.10	75.25	76.90
EN-B-GE-M	58.95	50.00	48.35	62.52	59.60	69.55	74.3	76.25
EN-B-JP-D	69.50	69.46	49.55	71.95	69.45	72.56	70.65	72.95
EN-B-JP-M	53.15	55.23	52.05	57.17	53.56	62.39	70.45	72.6
EN-D-FR-B	71.35	47.10	48.35	72.32	71.25	79.27	81.3	81.5
EN-D-FR-M	71.65	47.10	49.90	68.87	71.70	75.43	77.75	78.4
EN-D-GE-B	76.40	54.87	50.80	75.32	74.00	79.35	79.5	80.55
EN-D-GE-M	69.05	54.87	50.55	75.69	74.05	78.55	77.4	78.4
EN-D-JP-B	70.00	61.16	50.12	72.60	65.55	68.12	72.05	74.05
EN-D-JP-M	59.20	66.89	49.80	57.75	66.02	70.58	73.7	76.35
EN-M-FR-B	76.20	73.54	50.55	74.23	73.80	75.84	78.75	80.25
EN-M-FR-D	73.65	47.10	50.87	72.76	74.15	77.04	75.85	79.5
EN-M-GE-B	74.50	81.50	49.45	76.82	75.45	78.30	77.6	81.75
EN-M-GE-D	74.60	80.20	50.20	72.28	74.45	81.42	78.5	81.6
EN-B-JP-B	67.85	63.75	48.85	68.83	65.35	71.65	71.45	72.85
EN-B-JP-D	69.35	60.46	48.80	71.06	68.55	74.25	73.6	75.65