What is the class of this image ?

Discover the current state of the art in objects classification.

MNIST 50 results collected

Units: error %

Classify handwriten digits. Some additional results are available on the original dataset page.

Result	Method	Venue	Details
0.21%	Regularization of Neural Networks using DropConnect	ICML 2013
0.23%	Multi-column Deep Neural Networks for Image Classiﬁcation	CVPR 2012
0.23%	APAC: Augmented PAttern Classification with Neural Networks	arXiv 2015
0.24%	Batch-normalized Maxout Network in Network	arXiv 2015	Details (k=5 maxout pieces in each maxout unit).
0.29%	Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree	AISTATS 2016	Details Single model without data augmentation
0.31%	Recurrent Convolutional Neural Network for Object Recognition	CVPR 2015
0.31%	On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units	arXiv 2015
0.32%	Fractional Max-Pooling	arXiv 2015	Details Uses 12 passes at test time. Reaches 0.5% when using a single pass at test time.
0.33%	Competitive Multi-scale Convolution	arXiv 2015
0.35%	Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition	Neural Computation 2010	Details 6-layer NN 784-2500-2000-1500-1000-500-10 (on GPU), uses elastic distortions
0.35%	C-SVDDNet: An Effective Single-Layer Network for Unsupervised Feature Learning	arXiv 2014
0.37%	Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network	arXiv 2015	Details No data augmentation
0.39%	Efﬁcient Learning of Sparse Representations with an Energy-Based Model	NIPS 2006	Details Large conv. net, unsup pretraining, uses elastic distortions
0.39%	Convolutional Kernel Networks	arXiv 2014	Details No data augmentation.
0.39%	Deeply-Supervised Nets	arXiv 2014
0.4%	Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis	Document Analysis and Recognition 2003
0.40%	Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks	arXiv 2015
0.42%	Multi-Loss Regularized Deep Neural Network	CSVT 2015	Details Based on NiN architecture.
0.45%	Maxout Networks	ICML 2013	Details Uses convolution. Does not use dataset augmentation.
0.45%	Training Very Deep Networks	NIPS 2015	Details Best result selected on test set. 0.46% average over multiple trained models.
0.45%	ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks	arXiv 2015
0.46%	Deep Convolutional Neural Networks as Generic Feature Extractors	IJCNN 2015	Details feature extraction part of convnet is trained on imagenet (external training data), classification part is trained on cifar-10
0.47%	Network in Network	ICLR 2014	Details NIN + Dropout The code for NIN available at https://github.com/mavenlin/cuda-convnet
0.52 %	Trainable COSFIRE filters for keypoint detection and pattern recognition	PAMI 2013	Details Source code available.
0.53%	What is the Best Multi-Stage Architecture for Object Recognition?	ICCV 2009	Details Large conv. net, unsup pretraining, no distortions
0.54%	Deformation Models for Image Recognition	PAMI 2007	Details K-NN with non-linear deformation (IDM) (Preprocessing: shiftable edges)
0.54%	A trainable feature extractor for handwritten digit recognition	Journal Pattern Recognition 2007	Details Trainable feature extractor + SVMs, uses affine distortions
0.56%	Training Invariant Support Vector Machines	Machine Learning 2002	Details Virtual SVM, deg-9 poly, 2-pixel jittered (Preprocessing: deskewing)
0.59%	Simple Methods for High-Performance Digit Recognition Based on Sparse Coding	TNN 2008	Details Unsupervised sparse features + SVM, no distortions
0.62%	Unsupervised learning of invariant feature hierarchies with applications to object recognition	CVPR 2007	Details Large conv. net, unsup features, no distortions
0.62%	PCANet: A Simple Deep Learning Baseline for Image Classification?	arXiv 2014	Details No data augmentation.
0.63%	Shape matching and object recognition using shape contexts	PAMI 2002	Details K-NN, shape context matching (preprocessing: shape context feature extraction)
0.64%	Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features	CVPR 2012
0.68%	Handwritten Digit Recognition using Convolutional Neural Networks and Gabor Filters	ICCI 2003
0.69%	On Optimization Methods for Deep Learning	ICML 2011
0.71%	Deep Fried Convnets	ICCV 2015	Details Uses about 10x fewer parameters than the reference model, which reaches 0.87%.
0.75%	Sparse Activity and Sparse Connectivity in Supervised Learning	JMLR 2013
0.78%	Explaining and Harnessing Adversarial Examples	ICLR 2015	Details permutation invariant network used
0.82%	Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations	ICML 2009
0.84%	Supervised Translation-Invariant Sparse Coding	CVPR 2010	Details Uses sparse coding + svm.
0.94%	Large-Margin kNN Classification using a Deep Encoder Network	2009
0.95%	Deep Boltzmann Machines	AISTATS 2009
1.01%	BinaryConnect: Training Deep Neural Networks with binary weights during propagations	NIPS 2015	Details Using 50% dropout
1.1%	StrongNet: mostly unsupervised image recognition with strong neurons	technical report on ALGLIB website 2014	Details StrongNet is a neural design which uses two innovations: (a) “strong neurons” – highly nonlinear neurons with multiple outputs and (b) “mostly unsupervised architecture” – backpropagation-free design with all layers except for the last one being trained in a completely unsupervised setting.
1.12%	CS81: Learning words with Deep Belief Networks	2008
1.19%	Convolutional Neural Networks	2003	Details The ConvNN is based on the paper “Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis”.
1.2%	Reducing the dimensionality of data with neural networks	2006
1.40%	Convolutional Clustering for Unsupervised Learning	arXiv 2015	Details 2 layers + multi dict.
1.5%	Deep learning via semi-supervised embedding	2008
14.53%	Deep Representation Learning with Target Coding	AAAI 2015

Something is off, something is missing ? Feel free to fill in the form.

CIFAR-10 49 results collected

Units: accuracy %

Classify 32x32 colour images.

Result	Method	Venue	Details
96.53%	Fractional Max-Pooling	arXiv 2015	Details Uses 100 passes at test time. Reaches 95.5% when using a single pass at test time, and 96.33% when using 12 passes.. Uses data augmentation during training.
95.59%	Striving for Simplicity: The All Convolutional Net	ICLR 2015	Details 92% without data augmentation, 92.75% with small data augmentation, 95.59% when using agressive data augmentation and larger network.
94.16%	All you need is a good init	ICLR 2016	Details Only mirroring and random shifts, no extreme data augmentation. Uses thin deep residual net with maxout activations.
94%	Lessons learned from manually classifying CIFAR-10	unpublished 2011	Details Rough estimate from a single individual, over 400 training images (~1% of training data).
93.95%	Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree	AISTATS 2016	Details Single model with data augmentation, 92.38% without.
93.72%	Spatially-sparse convolutional neural networks	arXiv 2014
93.63%	Scalable Bayesian Optimization Using Deep Neural Networks	ICML 2015
93.57%	Deep Residual Learning for Image Recognition	arXiv 2015	Details Best performance reached with 110 layers. Using 1202 layers leads to 92.07%, 56 layers lead to 93.03%.
93.45%	Fast and Accurate Deep Network Learning by Exponential Linear Units	arXiv 2015	Details Without data augmentation.
93.34%	Universum Prescription: Regularization using Unlabeled Data	arXiv 2015
93.25%	Batch-normalized Maxout Network in Network	arXiv 2015	Details (k=5 maxout pieces in each maxout unit). Reaches 92.15% without data augmentation.
93.13%	Competitive Multi-scale Convolution	arXiv 2015
92.91%	Recurrent Convolutional Neural Network for Object Recognition	CVPR 2015	Details Reaches 91.31% without data augmentation.
92.49%	Learning Activation Functions to Improve Deep Neural Networks	ICLR 2015	Details Uses an adaptive piecewise linear activation function. 92.49% accuracy with data augmentation and 90.41% accuracy without data augmentation.
92.45%	cifar.torch	unpublished 2015	Details Code available at https://github.com/szagoruyko/cifar.torch
92.40%	Training Very Deep Networks	NIPS 2015	Details Best result selected on test set. 92.31% average over multiple trained models.
92.23%	Stacked What-Where Auto-encoders	arXiv 2015
91.88%	Multi-Loss Regularized Deep Neural Network	CSVT 2015	Details With data augmentation, 90.45% without. Based on NiN architecture.
91.78%	Deeply-Supervised Nets	arXiv 2014	Details Single model, with data augmentation: 91.78%. Without data augmentation: 90.22%.
91.73%	BinaryConnect: Training Deep Neural Networks with binary weights during propagations	NIPS 2015	Details These results were obtained without using any data-augmentation.
91.48%	On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units	arXiv 2015
91.40%	Spectral Representations for Convolutional Neural Networks	NIPS 2015
91.2%	Network In Network	ICLR 2014	Details The code for NIN available at https://github.com/mavenlin/cuda-convnet NIN + Dropout 89.6% NIN + Dropout + Data Augmentation 91.2%
91.19%	Speeding up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves	IJCAI 2015	Details Based on the “all convolutional” architecture. which reaches 90.92% by itself.
90.78%	Deep Networks with Internal Selective Attention through Feedback Connections	NIPS 2014	Details No data augmentation
90.68%	Regularization of Neural Networks using DropConnect	ICML 2013
90.65%	Maxout Networks	ICML 2013	Details This result was obtained using both convolution and synthetic translations / horizontal reflections of the training data. Reaches 88.32% when using convolution, but without any synthetic transformations of the training data.
90.61%	Improving Deep Neural Networks with Probabilistic Maxout Units	ICLR 2014	Details 65% without data augmentation. 61% when using data augmentation.
90.5%	Practical Bayesian Optimization of Machine Learning Algorithms	NIPS 2012	Details Reaches 85.02% without data augmentation. With data augmented with horizontal reﬂections and translations, 90.5% accuracy on test set is achieved.
89.67%	APAC: Augmented PAttern Classification with Neural Networks	arXiv 2015
89.14%	Deep Convolutional Neural Networks as Generic Feature Extractors	IJCNN 2015	Details feature extraction part of convnet is trained on imagenet (external training data), classification part is trained on cifar-10
89%	ImageNet Classification with Deep Convolutional Neural Networks	NIPS 2012	Details 87% error on the unaugmented data.
88.80%	Empirical Evaluation of Rectified Activations in Convolution Network	ICML workshop 2015	Details Using Randomized Leaky ReLU
88.79%	Multi-Column Deep Neural Networks for Image Classification	CVPR 2012	Details Supplemental material, Technical Report
87.65%	ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks	arXiv 2015
86.70 %	An Analysis of Unsupervised Pre-training in Light of Recent Advances	ICLR 2015	Details Unsupervised pre-training, with supervised fine-tuning. Uses dropout and data-augmentation.
84.87%	Stochastic Pooling for Regularization of Deep Convolutional Neural Networks	arXiv 2013
84.4%	Improving neural networks by preventing co-adaptation of feature detectors	arXiv 2012	Details So called “dropout” method.
83.96%	Discriminative Learning of Sum-Product Networks	NIPS 2012
82.9%	Stable and Efficient Representation Learning with Nonnegativity Constraints	ICML 2014	Details Full data, 3-layers + multi-dict. 4 with 3-layers only. 0 with 1-layers only.
82.2%	Learning Invariant Representations with Local Transformations	ICML 2012	Details K= 4,000
82.18%	Convolutional Kernel Networks	arXiv 2014	Details No data augmentation.
82%	Discriminative Unsupervised Feature Learning with Convolutional Neural Networks	NIPS 2014	Details Unsupervised feature learning + linear SVM
80.02%	Learning Smooth Pooling Regions for Visual Recognition	BMVC 2013
80%	Object Recognition with Hierarchical Kernel Descriptors	CVPR 2011
79.7%	Learning with Recursive Perceptual Representations	NIPS 2012	Details Code size 1600.
79.6 %	An Analysis of Single-Layer Networks in Unsupervised Feature Learning	AISTATS 2011	Details 6% obtained using K-means over whitened patches, with triangle encoding and 4000 features (clusters).
78.67%	PCANet: A Simple Deep Learning Baseline for Image Classification?	arXiv 2014	Details No data augmentation. Multiple feature scales combined. 77.14% when using only a single scale.
75.86%	Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network	arXiv 2015	Details No data augmentation

Something is off, something is missing ? Feel free to fill in the form.

CIFAR-100 31 results collected

Units: accuracy %

Classify 32x32 colour images.

Result	Method	Venue	Details
75.72%	Fast and Accurate Deep Network Learning by Exponential Linear Units	arXiv 2015	Details Without data augmentation.
75.7%	Spatially-sparse convolutional neural networks	arXiv 2014
73.61%	Fractional Max-Pooling	arXiv 2015	Details Uses 12 passes at test time. Reaches 68.55% when using a single pass at test time. Uses data augmentation during training.
72.60%	Scalable Bayesian Optimization Using Deep Neural Networks	ICML 2015
72.44%	Competitive Multi-scale Convolution	arXiv 2015
72.34%	All you need is a good init	ICLR 2015	Details Using RMSProp optimizer
71.14%	Batch-normalized Maxout Network in Network	arXiv 2015	Details (k=5 maxout pieces in each maxout unit).
70.80%	On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units	arXiv 2015
69.17%	Learning Activation Functions to Improve Deep Neural Networks	ICLR 2015	Details Uses a piecewise linear activation function. 69.17% accuracy with data augmentation and 65.6% accuracy without data augmentation.
69.12%	Stacked What-Where Auto-encoders	arXiv 2015
68.53%	Multi-Loss Regularized Deep Neural Network	CSVT 2015	Details With data augmentation, 65.82% without. Based on NiN architecture.
68.40%	Spectral Representations for Convolutional Neural Networks	NIPS 2015
68.25%	Recurrent Convolutional Neural Network for Object Recognition	CVPR 2015
67.76%	Training Very Deep Networks	NIPS 2015	Details Best result selected on test set. 67.61% average over multiple trained models.
67.68%	Deep Convolutional Neural Networks as Generic Feature Extractors	IJCNN 2015	Details feature extraction part of convnet is trained on imagenet (external training data), classification part is trained on cifar-100
67.63%	Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree	AISTATS 2016	Details Single model without data augmentation
67.38%	HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition	ICCV 2015
67.16%	Universum Prescription: Regularization using Unlabeled Data	arXiv 2015
66.29%	Striving for Simplicity: The All Convolutional Net	ICLR 2014
66.22%	Deep Networks with Internal Selective Attention through Feedback Connections	NIPS 2014
65.43%	Deeply-Supervised Nets	arXiv 2014	Details Single model, without data augmentation.
64.77%	Deep Representation Learning with Target Coding	AAAI 2015
64.32%	Network in Network	ICLR 2014	Details NIN + Dropout The code for NIN available at https://github.com/mavenlin/cuda-convnet
63.15%	Discriminative Transfer Learning with Tree-based Priors	NIPS 2013	Details The baseline “Convnet + max pooling + dropout” reaches 62.80% (without any tree prior).
61.86%	Improving Deep Neural Networks with Probabilistic Maxout Units	ICLR 2014
61.43%	Maxout Networks	ICML 2013	Details Uses convolution. Does not use dataset agumentation.
60.8%	Stable and Efficient Representation Learning with Nonnegativity Constraints	ICML 2014	Details 3-layers + multi-dict. 7 with 3-layers only. 3 with 1-layers only.
59.75%	Empirical Evaluation of Rectified Activations in Convolution Network	ICML workshop 2015	Details Using Randomized Leaky ReLU
57.49%	Stochastic Pooling for Regularization of Deep Convolutional Neural Networks	arXiv 2013
56.29%	Learning Smooth Pooling Regions for Visual Recognition	BMVC 2013	Details No data augmentation.
54.23%	Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features	CVPR 2012

Something is off, something is missing ? Feel free to fill in the form.

STL-10 18 results collected

Units: accuracy %

Similar to CIFAR-10 but with 96x96 images. Original dataset website.

Result	Method	Venue	Details
74.33%	Stacked What-Where Auto-encoders	arXiv 2015
74.10%	Convolutional Clustering for Unsupervised Learning	arXiv 2015	Details 3 layers + multi dict. With 2 layers, reaches 71.4%
73.15%	Deep Representation Learning with Target Coding	AAAI 2015
72.8% (±0.4%)	Discriminative Unsupervised Feature Learning with Convolutional Neural Networks	NIPS 2014	Details Unsupervised feature learning + linear SVM
70.20 % (±0.7 %)	An Analysis of Unsupervised Pre-training in Light of Recent Advances	ICLR 2015	Details Unsupervised pre-training, with supervised fine-tuning. Uses dropout and data-augmentation.
70.1% (±0.6%)	Multi-Task Bayesian Optimization	NIPS 2013	Details Also uses CIFAR-10 training data
68.23% ± 0.5	C-SVDDNet: An Effective Single-Layer Network for Unsupervised Feature Learning	arXiv 2014
68% (±0.55%)	Committees of deep feedforward networks trained with few data	arXiv 2014
67.9% (±0.6%)	Stable and Efficient Representation Learning with Nonnegativity Constraints	ICML 2014	Details 3-layers + multi-dict. 5 ± 0.5 with 3-layers only. 6 ± 0.6 with 1-layers only.
64.5% (±1%)	Unsupervised Feature Learning for RGB-D Based Object Recognition	ISER 2012	Details Hierarchical sparse coding using Matching Pursuit and K-SVD
62.32%	Convolutional Kernel Networks	arXiv 2014	Details No data augmentation.
62.3% (±1%)	Discriminative Learning of Sum-Product Networks	NIPS 2012
61.0% (±0.58%)	No more meta-parameter tuning in unsupervised sparse feature learning	arXiv 2014
61%	Deep Learning of Invariant Features via Simulated Fixations in Video	NIPS 2012 2012
60.1% (±1%)	Selecting Receptive Fields in Deep Networks	NIPS 2011
58.7%	Learning Invariant Representations with Local Transformations	ICML 2012
58.28%	Pooling-Invariant Image Feature Learning	arXiv 2012	Details 1600 codes, learnt using 2x PDL
56.5%	Deep Learning of Invariant Features via Simulated Fixations in Video	NIPS 2012	Details Trained also with video (unrelated to STL-10) obtained 61%

Something is off, something is missing ? Feel free to fill in the form.

SVHN 17 results collected

Units: error %

The Street View House Numbers (SVHN) Dataset.

SVHN is a real-world image dataset for developing machine learning and object recognition algorithms with minimal requirement on data preprocessing and formatting. It can be seen as similar in flavor to MNIST(e.g., the images are of small cropped digits), but incorporates an order of magnitude more labeled data (over 600,000 digit images) and comes from a significantly harder, unsolved, real world problem (recognizing digits and numbers in natural scene images). SVHN is obtained from house numbers in Google Street View images.

Result	Method	Venue	Details
1.69%	Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree	AISTATS 2016	Details Single model without data augmentation
1.76%	Competitive Multi-scale Convolution	arXiv 2015
1.77%	Recurrent Convolutional Neural Network for Object Recognition	CVPR 2015	Details Without data augmentation
1.81%	Batch-normalized Maxout Network in Network	arXiv 2015	Details (k=5 maxout pieces in each maxout unit).
1.92%	Deeply-Supervised Nets	arXiv 2014
1.92%	Multi-Loss Regularized Deep Neural Network	CSVT 2015	Details Based on NiN architecture.
1.94%	Regularization of Neural Networks using DropConnect	ICML 2013
1.97%	On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units	arXiv 2015
2%	Estimated human performance	NIPS 2011	Details Based on the paper that introduced the dataset Reading Digits in Natural Images with Unsupervised Feature Learning, section 5.
2.15%	BinaryConnect: Training Deep Neural Networks with binary weights during propagations	NIPS 2015
2.16%	Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks	ICLR 2014	Details For classification of individual digits with a single network, error rate is 2.16%. For classification of the entire digit sequence (first paper doing this): error rate of 3.97%.
2.35%	Network in Network	ICLR 2014	Details NIN + Dropout The code for NIN available at https://github.com/mavenlin/cuda-convnet
2.38%	ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks	arXiv 2015
2.47%	Maxout Networks	ICML 2013	Details This result was obtained using convolution but not any synthetic transformations of the training data.
2.8%	Stochastic Pooling for Regularization of Deep Convolutional Neural Networks	arXiv 2013	Details 64-64-128 Stochastic Pooling
3.96%	Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network	arXiv 2015	Details No data augmentation
4.9%	Convolutional neural networks applied to house numbers digit classiﬁcation	ICPR 2012	Details ConvNet / MS / L4 / Padded

Something is off, something is missing ? Feel free to fill in the form.

ILSVRC2012 task 1

Units: Error (5 guesses)

1000 categories classification challenge. With tens of thousands of training, validation and testing images.

See this interesting comparative analysis.

Results are collected in the following external webpage

Classification datasets results

What is the class of this image ?

MNIST
who is the best in MNIST ?

MNIST 50 results collected

CIFAR-10
who is the best in CIFAR-10 ?

CIFAR-10 49 results collected

CIFAR-100
who is the best in CIFAR-100 ?

CIFAR-100 31 results collected

STL-10
who is the best in STL-10 ?

STL-10 18 results collected

SVHN
who is the best in SVHN ?

SVHN 17 results collected

ILSVRC2012 task 1
who is the best in ILSVRC2012 task 1 ?

ILSVRC2012 task 1

Classification datasets results

What is the class of this image ?

MNISTwho is the best in MNIST ?

MNIST 50 results collected

CIFAR-10who is the best in CIFAR-10 ?

CIFAR-10 49 results collected

CIFAR-100who is the best in CIFAR-100 ?

CIFAR-100 31 results collected

STL-10who is the best in STL-10 ?

STL-10 18 results collected

SVHNwho is the best in SVHN ?

SVHN 17 results collected

ILSVRC2012 task 1who is the best in ILSVRC2012 task 1 ?

ILSVRC2012 task 1

MNIST
who is the best in MNIST ?

CIFAR-10
who is the best in CIFAR-10 ?

CIFAR-100
who is the best in CIFAR-100 ?

STL-10
who is the best in STL-10 ?

SVHN
who is the best in SVHN ?

ILSVRC2012 task 1
who is the best in ILSVRC2012 task 1 ?