Table 3.

Zero-shot learning results for the Standard Split (SS) and Proposed Split (PS) on SUN, CUB, AWA1, AWA2, and aPY datasets. We measure Top-1 accuracy in $\text{\%}$ for the results. †and ‡denote inductive and transductive settings respectively.

Methods		SUN		CUB		AWA1		AWA2		aPY
		SS	PS	SS	PS	SS	PS	SS	PS	SS	PS
	DAP [80]	38.9	39.9	37.5	40.0	57.1	44.1	58.7	46.1	35.2	33.8
	IAP [80]	17.4	19.4	27.1	24.0	48.1	35.9	46.9	35.9	22.4	36.6
	ConSE [113]	44.2	38.8	36.7	34.3	63.6	45.6	67.9	44.5	25.9	26.9
	CMT [157]	41.9	39.9	37.3	34.6	58.9	39.5	66.3	37.9	26.9	28.0
	SSE [204]	54.5	51.5	43.7	43.9	68.8	60.1	67.5	61.0	31.1	34.0
	LATEM [185]	56.9	55.3	49.4	49.3	74.8	55.1	68.7	55.8	34.5	35.2
	ALE [6]	59.1	58.1	53.2	54.9	78.6	59.9	80.3	62.5	30.9	39.7
	DeViSE [43]	57.5	56.5	53.2	52.0	72.9	54.2	68.6	59.7	35.4	39.8
†	SJE [7]	57.1	53.7	55.3	53.9	76.7	65.6	69.5	61.9	32.0	32.9
	ESZSL [137]	57.3	54.5	55.1	53.9	74.7	58.2	75.6	58.6	34.4	38.3
	SYNC [22]	59.1	56.3	54.1	55.6	72.2	54.0	71.2	46.6	39.7	23.9
	SAE [72]	42.4	40.3	33.4	33.3	80.6	53.0	80.7	54.1	8.3	8.3
	GFZSL [171]	62.9	60.6	53.0	49.3	80.5	68.3	79.3	63.8	51.3	38.4
	DEM [202]	–	61.9	–	51.7	–	68.4	–	67.1	–	35.0
	GAZSL [211]	–	61.3	–	55.8	–	68.2	–	68.4	–	41.1
	f-CLSWGAN [187]	–	60.8	–	57.3	–	68.8	–	68.2	–	40.5
	CVAE-ZSL [106]	–	61.7	–	52.1	–	71.4	–	65.8	–	–
	SE-ZSL [75]	64.5	63.4	60.3	59.6	83.8	69.5	80.8	69.2	–	–
	ALE-tran [6]	–	55.7	–	54.5	–	65.6	–	70.7	–	46.7
‡	GFZSL-tran [171]	–	64.0	–	49.3	–	81.3	–	78.6	–	37.1
	DSRL [197]	–	56.8	–	48.7	–	74.7	–	72.8	–	45.5