A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems | ✓ Link | 99.64 | | | µ2Net+ (ViT-L/16) | 2022-09-15 |
Revisiting a kNN-based Image Classification System with High-capacity Storage | | 99.6 | | | kNN-CLIP | 2022-04-03 |
SpinalNet: Deep Neural Network with Gradual Input | ✓ Link | 98.66 | | | Wide-ResNet-101 (Spinal FC) | 2020-07-07 |
Toward Understanding Supervised Representation Learning with RKHS and GAN | | 98.45 | | | CN(d=128) | 2021-01-01 |
Toward Understanding Supervised Representation Learning with RKHS and GAN | | 98.36 | | | CN(d=64) | 2021-01-01 |
Toward Understanding Supervised Representation Learning with RKHS and GAN | | 98.36 | | | NSRL+CN(d=128) | 2021-01-01 |
Toward Understanding Supervised Representation Learning with RKHS and GAN | | 98.34 | | | NSRL+CN(d=32) | 2021-01-01 |
Toward Understanding Supervised Representation Learning with RKHS and GAN | | 98.24 | | | NSRL+CN(d=64) | 2021-01-01 |
Toward Understanding Supervised Representation Learning with RKHS and GAN | | 98.17 | | | CN(d=32) | 2021-01-01 |
Neural Architecture Transfer | ✓ Link | 97.9 | 573M | 7.5M | NAT-M4 | 2020-05-12 |
Neural Architecture Transfer | ✓ Link | 97.8 | 436M | 7.5M | NAT-M3 | 2020-05-12 |
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision | ✓ Link | 97.3 | | 10000M | SEER (RegNet10B) | 2022-02-16 |
Neural Architecture Transfer | ✓ Link | 97.2 | 303M | 5.1M | NAT-M2 | 2020-05-12 |
Generative Pretraining from Pixels | ✓ Link | 97.1 | | | iGPT-L | 2020-07-17 |
Neural Architecture Transfer | ✓ Link | 96.7 | 240M | 4.4M | NAT-M1 | 2020-05-12 |
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations | ✓ Link | 95.48 | | | EnAET | 2019-11-21 |
SpinalNet: Deep Neural Network with Gradual Input | ✓ Link | 95.44 | | | VGG-19bn | 2020-07-07 |
Your Diffusion Model is Secretly a Zero-Shot Classifier | ✓ Link | 95.4 | | | Diffusion Classifier (zero-shot) | 2023-03-28 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 94.83 | | | FixMatch (CTA) | 2020-01-21 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 94.77 | | | ReMixMatch | 2020-01-21 |
Learning Representations by Maximizing Mutual Information Across Views | ✓ Link | 94.5 | | | AMDIM | 2019-06-03 |
MixMatch: A Holistic Approach to Semi-Supervised Learning | ✓ Link | 94.41 | | | MixMatch | 2019-05-06 |
Generative Pretraining from Pixels | ✓ Link | 94.2 | | | AMDIM-L | 2020-07-17 |
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring | ✓ Link | 93.82 | | | ReMixMatch (K=4) | 2019-11-21 |
A Framework For Contrastive Self-Supervised Learning And Designing A New Approach | ✓ Link | 93.80 | | | AMDIM | 2020-08-31 |
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring | ✓ Link | 93.23 | | | ReMixMatch (K=1) | 2019-11-21 |
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring | | 93.19 | | | MP* | 2020-07-03 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 92.34 | | | UDA | 2020-01-21 |
A Framework For Contrastive Self-Supervised Learning And Designing A New Approach | ✓ Link | 92.15 | | | YADIM | 2020-08-31 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 92.02 | | | FixMatch (RA) | 2020-01-21 |
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search | ✓ Link | 92.0 | | | NSGANetV2 | 2020-07-20 |
Scale-Equivariant Steerable Networks | ✓ Link | 91.49 | | | SESN | 2019-10-14 |
Harmonic Networks with Limited Training Samples | ✓ Link | 90.45 | | | Harmonic WRN-16-8 | 2019-04-30 |
General $E(2)$-Equivariant Steerable CNNs | ✓ Link | 90.20 | | | wrn16/8 D8 D4 D1 | 2019-11-19 |
DLME: Deep Local-flatness Manifold Embedding | ✓ Link | 90.1 | | | DLME (ResNet-50, linear) | 2022-07-07 |
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring | ✓ Link | 89.82 | | | MixMatch | 2019-11-21 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 89.59 | | | MixMatch | 2020-01-21 |
General $E(2)$-Equivariant Steerable CNNs | ✓ Link | 89.43 | | | wrn16/8* D8 D4 D1 | 2019-11-19 |
General $E(2)$-Equivariant Steerable CNNs | ✓ Link | 88.95 | | | wrn16/8* D1 D1 D1 | 2019-11-19 |
General $E(2)$-Equivariant Steerable CNNs | ✓ Link | 88.83 | | | wrn16/8 D1 D1 D1 | 2019-11-19 |
Invariant Information Clustering for Unsupervised Image Classification and Segmentation | ✓ Link | 88.8 | | | IIC | 2018-07-17 |
MixMatch: A Holistic Approach to Semi-Supervised Learning | ✓ Link | 88.80 | | | IIC | 2019-05-06 |
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods | ✓ Link | 88.08 | | | SOPCNN | 2020-01-24 |
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring | | 88.03 | | | TS | 2020-07-03 |
MixMatch: A Holistic Approach to Semi-Supervised Learning | ✓ Link | 87.36 | | | CutOut | 2019-05-06 |
Improved Regularization of Convolutional Neural Networks with Cutout | ✓ Link | 87.26 | | | Cutout | 2017-08-15 |
General $E(2)$-Equivariant Steerable CNNs | ✓ Link | 87.26 | | | wrn16/8 | 2019-11-19 |
Reversible Architectures for Arbitrarily Deep Residual Neural Networks | ✓ Link | 85.5 | | | Hamiltonian | 2017-09-12 |
Learning Class Unique Features in Fine-Grained Visual Classification | | 85.42 | | | ResNet-18+MM+FRL | 2020-11-22 |
Reversible Architectures for Arbitrarily Deep Residual Neural Networks | ✓ Link | 84.6 | | | MidPoint | 2017-09-12 |
Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM | | 84.38 | | | cosine function | 2018-01-01 |
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning | | 84.10 | | | HybridNet | 2018-07-30 |
Reversible Architectures for Arbitrarily Deep Residual Neural Networks | ✓ Link | 83.7 | | | Leapfrog | 2017-09-12 |
Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM | | 83.47 | | | skewing | 2018-01-01 |
Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM | | 83.45 | | | elastic distortion(2) | 2018-01-01 |
Probabilistic Structural Latent Representation for Unsupervised Embedding | | 83.2 | | | PSLR-knn | 2020-06-01 |
Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM | | 83.00 | | | elastic distortion(1) | 2018-01-01 |
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning | | 82.00 | | | ResNet baseline | 2018-07-30 |
Putting An End to End-to-End: Gradient-Isolated Learning of Representations | ✓ Link | 81.9 | | | Greedy InfoMax (GIM) | 2019-05-28 |
Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM | | 81.45 | | | rotation | 2018-01-01 |
Extended Batch Normalization | | 81.04 | | | ResNet18(BN, 4) | 2020-03-12 |
Training Neural Networks with Local Error Signals | ✓ Link | 80.75 | | | VGG8B + LocalLearning + CO | 2019-01-20 |
Extended Batch Normalization | | 79.3 | | | ResNet18(GN, 4) | 2020-03-12 |
Probabilistic Structural Latent Representation for Unsupervised Embedding | | 78.8 | | | PSLR-Linear | 2020-06-01 |
Extended Batch Normalization | | 78.65 | | | ResNet18(BN, 128) | 2020-03-12 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 78.57 | | | Mean Teacher | 2020-01-21 |
A Framework For Contrastive Self-Supervised Learning And Designing A New Approach | ✓ Link | 78.36 | | | CPC† | 2020-08-31 |
Deep Neural Networks Motivated by Partial Differential Equations | ✓ Link | 78.3 | | | Hamiltonian | 2018-04-12 |
Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks | ✓ Link | 77.8 | | | CC-GAN² | 2016-11-19 |
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring | ✓ Link | 77.80 | | | CC-GAN | 2019-11-21 |
Deep Neural Networks Motivated by Partial Differential Equations | ✓ Link | 77.0 | | | Parabolic | 2018-04-12 |
Scaling the Scattering Transform: Deep Hybrid Networks | ✓ Link | 76.6 | | | Scat + WRN 20-8 | 2017-03-27 |
Extended Batch Normalization | | 76.49 | | | ResNet18(EBN, 4) | 2020-03-12 |
Scaling the Scattering Transform: Deep Hybrid Networks | ✓ Link | 75.7 | | | Exemplar CNN | 2017-03-27 |
Extended Batch Normalization | | 75.57 | | | ResNet18(EBN, 128) | 2020-03-12 |
Scaling the Scattering Transform: Deep Hybrid Networks | ✓ Link | 74.33 | | | Stacked what-where AE | 2017-03-27 |
HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning | | 74.33 | | | SWWAE | 2018-07-30 |
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring | ✓ Link | 74.30 | | | SWWAE | 2019-11-21 |
Stacked What-Where Auto-encoders | ✓ Link | 74.3 | | | SWWAE | 2015-06-08 |
Deep Neural Networks Motivated by Partial Differential Equations | ✓ Link | 74.3 | | | Second-order | 2018-04-12 |
Convolutional Clustering for Unsupervised Learning | | 74.1 | | | Convolutional Clustering | 2015-11-19 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 73.77 | | | Π-Model | 2020-01-21 |
Discriminative Unsupervised Feature Learning with Convolutional Neural Networks | ✓ Link | 72.8 | | | Discriminative Unsupervised Feature Learning with Convolutional Neural Networks | 2014-12-01 |
Extended Batch Normalization | | 72.66 | | | ResNet18(GN, 128) | 2020-03-12 |
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence | ✓ Link | 72.01 | | | Pseudo-Labeling | 2020-01-21 |
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring | | 71.65 | | | Entropy | 2020-07-03 |
Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights | | 71.12 | | | BDW | 2020-06-22 |
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring | | 71.05 | | | MP | 2020-07-03 |
WaveMix: A Resource-efficient Neural Network for Image Analysis | ✓ Link | 70.88 | | | WaveMixLite-256/7 | 2022-05-28 |
Scaling the Scattering Transform: Deep Hybrid Networks | ✓ Link | 70.7 | | | CNN | 2017-03-27 |
An Analysis of Unsupervised Pre-training in Light of Recent Advances | ✓ Link | 70.2 | | | An Analysis of Unsupervised Pre-training in Light of Recent Advances | 2014-12-20 |
Multi-Task Bayesian Optimization | ✓ Link | 70.1 | | | Multi-Task Bayesian Optimization | 2013-12-01 |
Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights | | 69.15 | | | NN-Weighter | 2020-06-22 |
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring | | 68.62 | | | Accuracy Monitoring | 2020-07-03 |
Unsupervised Feature Learning with C-SVDDNet | | 68.2 | | | C-SVDDNet | 2014-12-23 |
Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights | | 68.19 | | | RotNet | 2020-06-22 |
Committees of deep feedforward networks trained with few data | | 68 | | | DFF Committees | 2014-06-23 |
Scaling the Scattering Transform: Deep Hybrid Networks | ✓ Link | 64.6 | | | Hierarchical Matching Pursuit (HMP) | 2017-03-27 |
Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights | | 63.13 | | | L2RW | 2020-06-22 |
Discriminative Learning of Sum-Product Networks | | 62.3 | | | Discriminative Learning of Sum-Product Networks | 2011-01-01 |
Convolutional Kernel Networks | | 62.3 | | | CKN | 2014-06-12 |
Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN) | | 61.94 | | | S-CNN | 2016-06-07 |
A Framework For Contrastive Self-Supervised Learning And Designing A New Approach | ✓ Link | 61 | | | Simulated Fixations | 2020-08-31 |
No more meta-parameter tuning in unsupervised sparse feature learning | | 61 | | | No more meta-parameter tuning in unsupervised sparse feature learning | 2014-02-24 |
Scaling the Scattering Transform: Deep Hybrid Networks | ✓ Link | 60.2 | | | Convolutional K-means Network | 2017-03-27 |
Receptive Fields without Spike-Triggering | | 60.1 | | | Receptive Fields | 2007-12-01 |
Effective Version Space Reduction for Convolutional Neural Networks | | 59.45 | | | PWD | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 59.33 | | | GVD | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 59.13 | | | VR | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 58.93 | | | Core SET | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 58.84 | | | GE | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 58.81 | | | DFAL | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 58.15 | | | Random | 2020-06-22 |
Effective Version Space Reduction for Convolutional Neural Networks | | 57.35 | | | BALD-MCD | 2020-06-22 |
How Important is Weight Symmetry in Backpropagation? | ✓ Link | 57.32 | | | Sign-symmetry | 2015-10-17 |
Effective Version Space Reduction for Convolutional Neural Networks | | 57.31 | | | M2-PWD | 2020-06-22 |
ICA with Reconstruction Cost for Efficient Overcomplete Feature Learning | | 52.9 | | | soft ica | 2011-12-01 |