Image Classification On Cifar 10

评估指标

Percentage correct

评测结果

各个模型在此基准测试上的表现结果

比较表格

模型名称	Percentage correct
andhra-bandersnatch-training-neural-networks	95.900
beta-rank-a-robust-convolutional-filter	93.97
imagenet-classification-with-deep	89
reduction-of-class-activation-uncertainty	99.05
vision-xformers-efficient-attention-for-image	79.50
empirical-evaluation-of-rectified-activations	88.8
trainable-activations-for-image	90.5
deep-residual-networks-with-exponential	94.4
incorporating-convolution-designs-into-visual	99.1
update-in-unit-gradient	99.13
when-vision-transformers-outperform-resnets	97.4
large-scale-evolution-of-image-classifiers	95.6
momentum-residual-neural-networks	95.18
unsupervised-learning-using-pretrained-cnn	83.1
an-evolutionary-approach-to-dynamic	99.49
multi-column-deep-neural-networks-for-image	88.8
spectral-representations-for-convolutional	91.4
autodropout-learning-dropout-patterns-to	97.9
ondev-lct-on-device-lightweight-convolutional	86.04
astroformer-more-data-might-not-be-all-you	99.12
renet-a-recurrent-neural-network-based	87.7
grouped-pointwise-convolutions-reduce	90.83
densenets-reloaded-paradigm-shift-beyond	99.31
regularizing-neural-networks-via-adversarial	98.02
discriminative-unsupervised-feature-learning-1	82
scalable-bayesian-optimization-using-deep	93.6
dynamic-routing-between-capsules	89.4
maxout-networks	90.65
splitnet-divide-and-co-training	98.38
apac-augmented-pattern-classification-with	89.7
transformer-in-transformer	99.1
convmlp-hierarchical-convolutional-mlps-for	98.6
non-convex-learning-via-replica-exchange	97.42
network-in-network	91.2
global-filter-networks-for-image	99.0
your-diffusion-model-is-secretly-a-zero-shot	88.5
regularizing-neural-networks-via-adversarial	96.03
when-vision-transformers-outperform-resnets	96.1
an-analysis-of-unsupervised-pre-training-in	86.7
competitive-multi-scale-convolution	93.1
noisy-differentiable-architecture-search	97.61
pso-convolutional-neural-networks-with	98.31
lets-keep-it-simple-using-simple	95.51
sparseswin-swin-transformer-with-sparse	97.43
practical-bayesian-optimization-of-machine	90.5
performance-of-gaussian-mixture-model	-
large-scale-evolution-of-image-classifiers	94.6
adaptive-split-fusion-transformer	98.7
automatic-data-augmentation-via-invariance	97.85
pdo-econvs-partial-differential-operator	94.35
all-you-need-is-a-good-init	94.2
an-optimized-toolbox-for-advanced-image	82.8
vision-models-are-more-robust-and-fair-when	90
training-very-deep-networks	92.4
levit-a-vision-transformer-in-convnet-s	97.5
convolutional-kernel-networks	82.2
trainable-activations-for-image	88.8
when-vision-transformers-outperform-resnets	98.2
how-to-use-dropout-correctly-on-residual	94.4367
mish-a-self-regularized-non-monotonic-neural	94.05
levit-a-vision-transformer-in-convnet-s	97.6
automatic-data-augmentation-via-invariance	97.05
non-convex-learning-via-replica-exchange	95.35
transboost-improving-the-best-imagenet	97.61
dinov2-learning-robust-visual-features	99.5
averaging-weights-leads-to-wider-optima-and	97.12
sparse-networks-from-scratch-faster-training	95.04
when-vision-transformers-outperform-resnets	98.6
fast-denser-evolving-fully-trained-deep	88.73
cutmix-regularization-strategy-to-train	97.12
andhra-bandersnatch-training-neural-networks	95.536
learning-with-recursive-perceptual	79.7
trainable-activations-for-image	86.5
deep-pyramidal-residual-networks	96.69
pcanet-a-simple-deep-learning-baseline-for	78.7
encoding-the-latent-posterior-of-bayesian	95.02
when-vision-transformers-outperform-resnets	98.2
batch-normalized-maxout-network-in-network	93.3
fractional-max-pooling	96.5
an-image-is-worth-16x16-words-transformers-1	99.5
economical-ensembles-with-hypernetworks	96.81
densely-connected-convolutional-networks	96.54
on-the-performance-analysis-of-momentum	95.66
proxylessnas-direct-neural-architecture	97.92
understanding-and-enhancing-mixed-sample-data	98.64
neural-architecture-search-with-reinforcement	96.4
unsupervised-representation-learning-with-1	82.8
personalized-federated-learning-with-hidden	80.63
dlme-deep-local-flatness-manifold-embedding	91.3
vision-xformers-efficient-attention-for-image	75.26
preventing-manifold-intrusion-with-locality	95.97
efficientnet-rethinking-model-scaling-for	98.9
im-loss-information-maximization-loss-for	95.49
noisy-differentiable-architecture-search	98.28
distilled-gradual-pruning-with-pruned-fine	92.90
learning-implicitly-recurrent-cnns-through	97.47
when-vision-transformers-outperform-resnets	97.8
context-aware-deep-model-compression-for-edge	92.01
efficient-adaptive-ensembling-for-image	-
stochastic-optimization-of-plain	94.29
single-bit-per-weight-deep-convolutional	96.71
striving-for-simplicity-the-all-convolutional	95.6
ondev-lct-on-device-lightweight-convolutional	87.65
identity-mappings-in-deep-residual-networks	95.4
efficientnetv2-smaller-models-and-faster	99.0
mixup-beyond-empirical-risk-minimization	97.3
gradinit-learning-to-initialize-neural	94.71
vision-xformers-efficient-attention-for-image	83.36
averaging-weights-leads-to-wider-optima-and	96.79
on-the-importance-of-normalisation-layers-in	91.5
convmlp-hierarchical-convolutional-mlps-for	98
trainable-activations-for-image	90.9
mish-a-self-regularized-non-monotonic-neural	92.02
wavemix-multi-resolution-token-mixing-for	85.21
revisiting-a-knn-based-image-classification	97.3
online-training-through-time-for-spiking	93.73
universum-prescription-regularization-using	93.3
levit-a-vision-transformer-in-convnet-s	98
bamboo-building-mega-scale-vision-dataset	98.2
deep-networks-with-internal-selective	90.8
large-scale-learning-of-general-visual	99.37
pdo-econvs-partial-differential-operator	94.62
trainable-activations-for-image	89.0
learning-hyperparameters-via-a-data	98.2
grouped-pointwise-convolutions-reduce	93.75
stacked-what-where-auto-encoders	92.2
with-a-little-help-from-my-friends-nearest	93.7
automix-unveiling-the-power-of-mixup	97.84
pdo-econvs-partial-differential-operator	96.32
knowledge-representing-efficient-sparse	90.65
an-enhanced-scheme-for-reducing-the	94.95
batchboost-regularization-for-stabilizing	97.54
vision-xformers-efficient-attention-for-image	83.26
training-data-efficient-image-transformers	99.1
non-convex-learning-via-replica-exchange	96.87
cnn-filter-db-an-empirical-investigation-of	94.79
non-convex-learning-via-replica-exchange	96.12
模型 138	95.32
vision-xformers-efficient-attention-for-image	74
srm-a-style-based-recalibration-module-for	95.05
neural-architecture-transfer	98.2
vision-xformers-efficient-attention-for-image	65.06
efficientnetv2-smaller-models-and-faster	98.7
gated-convolutional-networks-with-hybrid	97.86
rmdl-random-multimodel-deep-learning-for	91.21
training-neural-networks-with-local-error	96.4
threshold-pruning-tool-for-densely-connected	86.34
upanets-learning-from-the-universal-pixel	96.47
pre-training-of-lightweight-vision	96.41
how-important-is-weight-symmetry-in	80.98
towards-principled-design-of-deep	96.29
threshnet-an-efficient-densenet-using	86.69
wavemix-lite-a-resource-efficient-neural	97.29
benchopt-reproducible-efficient-and	95.55
augmented-neural-odes	60.6
a-bregman-learning-framework-for-sparse	92.3
squeeze-and-excitation-networks	97.88
incorporating-convolution-designs-into-visual	99
spatially-sparse-convolutional-neural	93.7
splitnet-divide-and-co-training	98.32
improving-deep-neural-networks-with	90.6
sag-vit-a-scale-aware-high-fidelity-patching	-
andhra-bandersnatch-training-neural-networks	96.088
patches-are-all-you-need-1	96.74
selective-kernel-networks	96.53
gated-convolutional-networks-with-hybrid	96.85
convolutional-xformers-for-vision	94.46
gated-convolutional-networks-with-hybrid	97.71
three-things-everyone-should-know-about	99.3
improving-neural-networks-by-preventing-co	84.4
mixmatch-a-holistic-approach-to-semi	95.05
neural-architecture-transfer	98.4
levit-a-vision-transformer-in-convnet-s	98.2
andhra-bandersnatch-training-neural-networks	94.118
trainable-activations-for-image	91.1
rethinking-recurrent-neural-networks-and	98.52
enaet-self-trained-ensemble-autoencoding	98.01
deep-convolutional-neural-networks-as-generic	89.1
binaryconnect-training-deep-neural-networks	91.7
gated-attention-coding-for-training-high	96.46
densenets-reloaded-paradigm-shift-beyond	98.88
neural-architecture-transfer	97.9
deep-complex-networks	94.4
non-convex-learning-via-replica-exchange	94.62
deep-competitive-pathway-networks	96.62
grouped-pointwise-convolutions-reduce	92.74
trainable-activations-for-image	90.4
densenets-reloaded-paradigm-shift-beyond	99.31
splitnet-divide-and-co-training	98.31
learning-local-discrete-features-in	94.15
ondev-lct-on-device-lightweight-convolutional	87.03
fast-autoaugment	98.3
an-algorithm-for-routing-vectors-in-sequences	99.2
xnodr-and-xnidr-two-accurate-and-fast-fully	96.87
levit-a-vision-transformer-in-convnet-s	98.1
deeply-supervised-nets	91.8
fixup-initialization-residual-learning	97.7
enhanced-image-classification-with-a-fast	75.9
autodropout-learning-dropout-patterns-to	96.8
mixmo-mixing-multiple-inputs-for-multiple	97.73
evaluating-the-performance-of-taaf-for-image	82.06
learning-activation-functions-to-improve-deep	92.5
sneaky-spikes-uncovering-stealthy-backdoor	68.3
flexconv-continuous-kernel-convolutions-with-1	92.2
模型 205	78.9
learning-identity-mappings-with-residual	96.35
manifold-mixup-better-representations-by	97.45
grouped-pointwise-convolutions-reduce	89.81
aggregating-nested-transformers	97.2
efficientnetv2-smaller-models-and-faster	99.1
cvt-introducing-convolutions-to-vision	99.39
economical-ensembles-with-hypernetworks	97.45
ondev-lct-on-device-lightweight-convolutional	85.73
deep-polynomial-neural-networks	94.9
deep-networks-with-stochastic-depth	94.77
connection-reduction-is-all-you-need	86.64
on-the-relationship-between-self-attention-1	93.8
neural-architecture-transfer	97.4
adaptive-split-fusion-transformer	98.8%
sample-efficient-neural-architecture-search-1	99.03
vision-xformers-efficient-attention-for-image	76.9
tokenmixup-efficient-attention-guided-token	97.78
exact-how-to-train-your-accuracy	96.73
learning-in-wilson-cowan-model-for	86.59
human-interpretable-ai-enhancing-tsetlin	75.1
not-all-images-are-worth-16x16-words-dynamic	98.53
effect-of-large-scale-pre-training-on-full	97.82
stochastic-pooling-for-regularization-of-deep	84.9
tresnet-high-performance-gpu-dedicated	99
incorporating-convolution-designs-into-visual	98.5
ondev-lct-on-device-lightweight-convolutional	84.55
aggregated-pyramid-vision-transformer-split	80.45
large-scale-learning-of-general-visual	98.91
gpipe-efficient-training-of-giant-neural	99
an-image-is-worth-16x16-words-transformers-1	99.42
going-deeper-with-image-transformers	99.4
ondev-lct-on-device-lightweight-convolutional	86.27
splitnet-divide-and-co-training	98.71
ondev-lct-on-device-lightweight-convolutional	86.64
pdo-econvs-partial-differential-operator	96.5
towards-class-specific-unit	95.33
asam-adaptive-sharpness-aware-minimization	98.68
smoothnets-optimizing-cnn-architecture-design	73.5
generalizing-pooling-functions-in	94.0
triplenet-a-low-computing-power-platform-of	87.03
unsupervised-representation-learning-with-1	80.6
stochastic-subsampling-with-average-pooling	93.861
autoformer-searching-transformers-for-visual	99.1
effect-of-large-scale-pre-training-on-full	95.78
muxconv-information-multiplexing-in	98.0
resnet-strikes-back-an-improved-training	85.28
oriented-response-networks	97.02
loss-sensitive-generative-adversarial	91.7
fast-and-accurate-deep-network-learning-by	93.5
andhra-bandersnatch-training-neural-networks	96.378
escaping-the-big-data-paradigm-with-compact	95.29
resnet-strikes-back-an-improved-training	98.3
escaping-the-big-data-paradigm-with-compact	98
convmlp-hierarchical-convolutional-mlps-for	98.6
context-aware-compilation-of-dnn-training	95.16
efficient-architecture-search-by-network	94.6
bnn-bn-training-binary-neural-networks	92.08
ondev-lct-on-device-lightweight-convolutional	86.61
patches-are-all-you-need-1	96.03