Image Classification On Cifar 100

Metrics

Percentage correct

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	Percentage correct
stochastic-pooling-for-regularization-of-deep	57.5
non-convex-learning-via-replica-exchange	84.38
on-the-importance-of-normalisation-layers-in	70.8
three-things-everyone-should-know-about	93.0
deep-competitive-pathway-networks	81.10
autoaugment-learning-augmentation-policies	89.3
dianet-dense-and-implicit-attention-network	76.98
Model 8	85.25
differentiable-spike-rethinking-gradient	74.24
res2net-a-new-multi-scale-backbone	83.44
expeditious-saliency-guided-mix-up-through	83.97
pre-training-of-lightweight-vision	78.27
expeditious-saliency-guided-mix-up-through	80.75
pdo-econvs-partial-differential-operator	73
cnn-filter-db-an-empirical-investigation-of	75.59
large-scale-learning-of-general-visual	92.17
learning-identity-mappings-with-residual	81.73
sharpness-aware-minimization-for-efficiently-1	89.7
resmlp-feedforward-networks-for-image	89.5
andhra-bandersnatch-training-neural-networks	78.792
unsharp-masking-layer-injecting-prior	60.36
sparseswin-swin-transformer-with-sparse	85.35
gated-convolutional-networks-with-hybrid	81.87
sagemix-saliency-guided-mixup-for-point	80.16
sharpness-aware-quantization-for-deep-neural	35.05
andhra-bandersnatch-training-neural-networks	73.930
stochastic-optimization-of-plain	72.96
incorporating-convolution-designs-into-visual	89.4
sharpness-aware-minimization-for-efficiently-1	42.64
2003-13549	77.7
efficient-adaptive-ensembling-for-image	-
when-vision-transformers-outperform-resnets	86.4
andhra-bandersnatch-training-neural-networks	82.784
deep-networks-with-stochastic-depth	75.42
andhra-bandersnatch-training-neural-networks	80.354
not-all-images-are-worth-16x16-words-dynamic	89.63
expeditious-saliency-guided-mix-up-through	85
wide-residual-networks	81.15
reduction-of-class-activation-uncertainty	93.31
an-evolutionary-approach-to-dynamic	94.95
striving-for-simplicity-the-all-convolutional	66.3
astroformer-more-data-might-not-be-all-you	93.36
sharpness-aware-minimization-for-efficiently-1	96.08
bnn-bn-training-binary-neural-networks	68.34
mixmo-mixing-multiple-inputs-for-multiple	86.81
self-knowledge-distillation-a-simple-way-for	86.41
revisiting-a-knn-based-image-classification	81.7
resnet50-on-cifar-100-without-transfer	67.060
learning-the-connections-in-direct-feedback	66.78
cvt-introducing-convolutions-to-vision	94.09
tresnet-high-performance-gpu-dedicated	92.6
automatic-data-augmentation-via-invariance	84.89
incorporating-convolution-designs-into-visual	91.8
grafit-learning-fine-grained-image	83.7
upanets-learning-from-the-universal-pixel	80.29
network-in-network	64.3
training-data-efficient-image-transformers	90.8
expeditious-saliency-guided-mix-up-through	82.16
hd-cnn-hierarchical-deep-convolutional-neural	67.4
beta-rank-a-robust-convolutional-filter	74.01
splitnet-divide-and-co-training	87.44
stochastic-subsampling-with-average-pooling	72.537
aggregating-nested-transformers	82.56
when-vision-transformers-outperform-resnets	89.1
single-bit-per-weight-deep-convolutional	82.95
towards-principled-design-of-deep	80.29
fatnet-high-resolution-kernels-for	60
an-algorithm-for-routing-vectors-in-sequences	93.8
all-you-need-is-a-good-init	72.3
gated-convolutional-networks-with-hybrid	84.04
fatnet-high-resolution-kernels-for	60
with-a-little-help-from-my-friends-nearest	79
splitnet-divide-and-co-training	85.74
deep-feature-response-discriminative	86.31
discriminative-transfer-learning-with-tree	63.2
mixmo-mixing-multiple-inputs-for-multiple	85.77
online-training-through-time-for-spiking	71.05
wavemix-lite-a-resource-efficient-neural	70.20
pdo-econvs-partial-differential-operator	79.99
tokenmixup-efficient-attention-guided-token	83.57
learning-the-connections-in-direct-feedback	48.03
pdo-econvs-partial-differential-operator	81.6
global-filter-networks-for-image	90.3
gpipe-efficient-training-of-giant-neural	91.3
maxout-networks	61.43
generalizing-pooling-functions-in	67.6
averaging-weights-leads-to-wider-optima-and	82.15
Model 88	85.59
identity-mappings-in-deep-residual-networks	77.3
incorporating-convolution-designs-into-visual	88
efficientnetv2-smaller-models-and-faster	92.3
non-convex-learning-via-replica-exchange	82.95
improving-deep-neural-networks-with	61.9
automix-unveiling-the-power-of-mixup	85.16
resmlp-feedforward-networks-for-image	87.0
mish-a-self-regularized-non-monotonic-neural	74.41
resnet-strikes-back-an-improved-training	86.9
automix-unveiling-the-power-of-mixup	83.64
label-ranker-self-aware-preference-for	-
densely-connected-convolutional-networks	82.62
expeditious-saliency-guided-mix-up-through	82.43
splitnet-divide-and-co-training	89.46
convmlp-hierarchical-convolutional-mlps-for	89.1
large-scale-learning-of-general-visual	93.51
fast-and-accurate-deep-network-learning-by	75.7
oriented-response-networks	83.85
efficientnetv2-smaller-models-and-faster	92.2
non-convex-learning-via-replica-exchange	74.14
squeeze-and-excitation-networks	84.59
im-loss-information-maximization-loss-for	70.18
bamboo-building-mega-scale-vision-dataset	90.2
escaping-the-big-data-paradigm-with-compact	82.72
ml-decoder-scalable-and-versatile	95.1
neural-architecture-transfer	86.0
understanding-and-enhancing-mixed-sample-data	83.95
vision-models-are-more-robust-and-fair-when	81.53
deep-residual-networks-with-exponential	73.5
expeditious-saliency-guided-mix-up-through	81.79
learning-implicitly-recurrent-cnns-through	82.57
fatnet-high-resolution-kernels-for	66
rethinking-recurrent-neural-networks-and	90.27
colornet-investigating-the-importance-of	88.4
towards-class-specific-unit	76.64
densely-connected-convolutional-networks	82.82
fast-autoaugment	88.3
going-deeper-with-image-transformers	93.1
puzzle-mix-exploiting-saliency-and-local-1	84.05
expeditious-saliency-guided-mix-up-through	82.3
incorporating-convolution-designs-into-visual	91.8
Model 130	85.38
scalable-bayesian-optimization-using-deep	72.6
automatic-data-augmentation-via-invariance	81.19
convmlp-hierarchical-convolutional-mlps-for	87.4
competitive-multi-scale-convolution	72.4
momentum-residual-neural-networks	76.38
pso-convolutional-neural-networks-with	87.48
economical-ensembles-with-hypernetworks	85.00
attend-and-rectify-a-gated-attention	82.18
improving-neural-architecture-search-image	85.42
stacked-what-where-auto-encoders	69.1
non-convex-learning-via-replica-exchange	76.55
convmlp-hierarchical-convolutional-mlps-for	88.6
learning-the-connections-in-direct-feedback	19.49
expeditious-saliency-guided-mix-up-through	84.9
imagenet-21k-pretraining-for-the-masses	94.2
empirical-evaluation-of-rectified-activations	59.8
exact-how-to-train-your-accuracy	82.68
how-important-is-weight-symmetry-in	48.75
training-very-deep-networks	67.8
selective-kernel-networks	82.67
non-convex-learning-via-replica-exchange	80.14
expeditious-saliency-guided-mix-up-through	83.02
economical-ensembles-with-hypernetworks	83.06
convolutional-xformers-for-vision	60.11
lets-keep-it-simple-using-simple	78.37
boosting-discriminative-visual-representation	85.50
eeea-net-an-early-exit-evolutionary-neural	84.98
polynomial-networks-in-deep-classifiers	77.9
universum-prescription-regularization-using	67.2
mixup-beyond-empirical-risk-minimization	83.20
when-vision-transformers-outperform-resnets	85.2
manifold-mixup-better-representations-by	81.96
efficientnet-rethinking-model-scaling-for	91.7
cutmix-regularization-strategy-to-train	86.19
expeditious-saliency-guided-mix-up-through	82.32
mixmatch-a-holistic-approach-to-semi	74.1
transformer-in-transformer	91.1
neural-architecture-transfer	87.7
encoding-the-latent-posterior-of-bayesian	76.85
muxconv-information-multiplexing-in	86.1
update-in-unit-gradient	93.95
andhra-bandersnatch-training-neural-networks	80.830
averaging-weights-leads-to-wider-optima-and	84.16
training-neural-networks-with-local-error	79.9
deep-convolutional-decision-jungle-for-image	69
regularizing-neural-networks-via-adversarial	86.64
when-vision-transformers-outperform-resnets	87.6
how-to-use-dropout-correctly-on-residual	73.98
neural-architecture-transfer	88.3
when-vision-transformers-outperform-resnets	82.4
performance-of-gaussian-mixture-model	-
batch-normalized-maxout-network-in-network	71.1
enaet-self-trained-ensemble-autoencoding	83.13
effect-of-large-scale-pre-training-on-full	88.54
spectral-representations-for-convolutional	68.4
sharpness-aware-minimization-for-efficiently-1	36.07
fractional-max-pooling	73.6
asam-adaptive-sharpness-aware-minimization	89.90
190409925	81.6
dlme-deep-local-flatness-manifold-embedding	66.1
learning-activation-functions-to-improve-deep	69.2
spatially-sparse-convolutional-neural	75.7
wavemix-lite-a-resource-efficient-neural	85.09
boosting-discriminative-visual-representation	84.42
large-scale-evolution-of-image-classifiers	77
regularizing-neural-networks-via-adversarial	78.49
deep-convolutional-neural-networks-as-generic	67.7
splitnet-divide-and-co-training	86.90
escaping-the-big-data-paradigm-with-compact	77.31
efficientnetv2-smaller-models-and-faster	91.5
gated-convolutional-networks-with-hybrid	83.46
neural-architecture-transfer	87.5
on-the-performance-analysis-of-momentum	81.44
expeditious-saliency-guided-mix-up-through	81.49
deeply-supervised-nets	65.4
gated-attention-coding-for-training-high	80.45
pdo-econvs-partial-differential-operator	72.87
grouped-pointwise-convolutions-reduce	71.36
contextual-classification-using-self	83.2
expeditious-saliency-guided-mix-up-through	80.6