Deep Polynomial Neural Networks

Deep Convolutional Neural Networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few)... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Face Recognition CFP-FF Prodpoly Accuracy 99.886 # 1
Face Recognition CFP-FP Prodpoly Accuracy 98.986 # 1
Image Generation CIFAR-10 ProdPoly Inception score 8.49 # 22
FID 16.79 # 32
Image Generation CIFAR-10 ProdPoly no activation functions Inception score 6.95 # 41
FID 40.45 # 48
Image Classification CIFAR-10 Prodpoly Percentage correct 94.9 # 83
Conditional Image Generation CIFAR-10 ProdPoly no activation functions Inception score 7.5 # 12
FID 36.77 # 10
Image Classification ImageNet Prodpoly Top 1 Accuracy 77.17% # 276
Top 5 Accuracy 93.56% # 145
Face Recognition LFW Prodpoly Accuracy 99.833 # 1
Face Identification MegaFace Prodpoly Accuracy 98.78% # 2
Face Verification MegaFace Prodpoly Accuracy 98.95% # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet