CIFAR-100

	A	B	C	D	E	F	G
1	Rank	Method	Percentage Correct	Percentage Error	Date	Other dataset	added by us

2	1	EfficientNet	91.7	8.3	2019-05-28	WAHR
3	2	GPIPE	91.3	8.7	2018-11-16	WAHR
4	3	AutoAugment	89.93	10.07	2019-04-19	FALSCH	WAHR
5	4	PyramidNet-200 + Shakedrop + Cutmix	86.19	13.81	2019-05-13	FALSCH
6	5	ASANas	85.42	14.58	2019-01-25	FALSCH	WAHR
7	6	Shake-shake regularization + cutout	84.8	15.2	2017-11-29	FALSCH
8	7	SENet + ShakeEven + Cutout	84.59	15.41	2017-09-05	FALSCH
9	8	PyramidNet-272 + SWA	84.16	15.84	2018-03-14	FALSCH	WAHR
10	9	PyramidNet + ShakeDrop	83.78	16.22	2018-12-04	FALSCH	WAHR
11	10	AutoAugment + DropActivation	83.8	16.2	2019-06-03	FALSCH
12	11	Res2NeXt-29	83.44	16.56	2019-04-02	FALSCH
13	12	DenseNet-BC-190 + Mixup	83.2	16.8	2017-10-25	FALSCH
14	13	Wide ResNet+Cutout+no BN scale/offset learning	82.95	17.05	2019-07-16	FALSCH
15	14	DenseNet	82.62	17.38	2016-08-25	FALSCH
16	15	Shared WRN	82.57	17.43	2019-02-26	FALSCH
17	16	WRN+SWA	82.15	17.85	2018-03-14	FALSCH
18	17	Manifold Mixup	81.96	18.04	2018-06-13	FALSCH
19	18	Residual Gates + WRN	81.73	18.27	2016-11-04	FALSCH
20	19	AA-Wide-ResNet	81.6	18.4	2019-04-22	FALSCH
21	20	Wide ResNet	81.15	18.85	2016-05-23	FALSCH
22	21	CoPaNet-R-164	81.1	18.9	2017-09-29	FALSCH
23	22	SimpleNetv2	80.29	19.71	2018-02-17	FALSCH
24	23	VGG11B(3x)+LocalLearning	79.9	20.1	2019-01-20	FALSCH
25	24	SimpleNetv1	78.37	21.63	2016-08-22	FALSCH
26	25	ResNet-1001	77.3	22.7	2016-03-16	FALSCH
27	26	Evolution	77	23	2017-03-03	FALSCH
28	27	DIANet	76.98	23.02	2019-05-25	FALSCH
29	28	SSCNN	75.7	24.3	2014-09-22	FALSCH
30	29	Exponential Linear Units	75.7	24.3	2015-11-23	FALSCH
31	30	Stochastic Depth	75.42	24.58	2016-03-30	FALSCH
32	31	ResNet v2-110 (Mish activation)	74.41	25.59	2019-08-23	FALSCH
33	32	Fractional MP	73.6	26.4	2014-12-18	FALSCH
34	33	ResNet+ELU	73.5	26.5	2016-04-14	FALSCH
35	34	Deep Complex	72.9	27.1	2017-05-27	FALSCH
36	35	Tuned CNN	72.6	27.4	2015-02-19	FALSCH
37	36	CMsC	72.4	27.6	2015-11-18	FALSCH
38	37	Fitnet4-LSUV	72.3	27.7	2015-11-19	FALSCH
39	38	BNM NiN	71.1	28.9	2015-11-09	FALSCH
40	39	MIM	70.8	29.2	2015-08-03	FALSCH
41	40	NiN+APL	69.2	30.8	2014-12-21	FALSCH
42	41	SWWAE	69.1	30.9	2015-06-08	FALSCH
43	42	NiN+Superclass+CDJ	69	31	2017-06-06	FALSCH
44	43	MLR DNN	68.5	31.5		FALSCH
45	44	Spectral Representations for Convolutional Neural Networks	68.4	31.6	2015-12-01	FALSCH
46	45	RCNN-96	68.3	31.7		FALSCH
47	46	VDN	67.8	32.2	2015-07-22	FALSCH
48	47	DCNN+GFE	67.7	32.3	2017-10-06	FALSCH
49	48	Tree+Max-Avg pooling	67.6	32.4	2015-09-30	FALSCH
50	49	HD-CNN	67.4	32.6	2014-10-03	FALSCH
51	50	Universum Prescription	67.2	32.8	2015-11-11	FALSCH
52	51	ACN	66.3	33.7	2014-12-21	FALSCH
53	52	Deep Networks with Internal Selective Attention through Feedback Connections	66.2	33.8	2014-12-01	FALSCH
54	53	DSN	65.43	34.57	2014-09-18	FALSCH
55	54	Deep Representation Learning with Target Coding	64.8	35.2		FALSCH
56	55	NiN	64.32	35.68	2013-12-16	FALSCH
57	56	Tree Priors	63.2	36.8	2013-12-01	FALSCH
58	57	DNN+Probabilistic Maxout	61.9	38.1	2013-12-20	FALSCH
59	58	Maxout Network (k=2)	61.43	38.57	2013-02-18	FALSCH
60	59	Stable and Efficient Representation Learning with Nonnegativity Constraints	60.8	39.2		FALSCH
61	60	ResNet20+UnsharpMaskLayer	60.36	39.64	2019-09-29	FALSCH
62	61	RReLU	59.8	40.2	2015-05-05	FALSCH
63	62	Stochastic Pooling	57.5	42.5	2013-01-16	FALSCH
64	63	Smooth Pooling Regions	56.3	43.7		FALSCH
65	64	Receptive Field Learning	54.2	45.8		FALSCH
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100