Residual networks reformulate layers to learn residual functions, enabling effective training of up to 152-layer models that achieve 3.57% error on ImageNet and win ILSVRC 2015.
Maxout networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
DCGANs with architectural constraints learn a hierarchy of representations from object parts to scenes in both generator and discriminator across image datasets.
The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion realizing effective attacks that transfer across comparators.
Graph Laplacian interpolating activation replaces softmax in DNNs and improves natural accuracy, robust accuracy, and data efficiency.
A 2019 survey of machine reading comprehension corpora and methods.
citing papers explorer
-
Deep Residual Learning for Image Recognition
Residual networks reformulate layers to learn residual functions, enabling effective training of up to 152-layer models that achieve 3.57% error on ImageNet and win ILSVRC 2015.
-
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
DCGANs with architectural constraints learn a hierarchy of representations from object parts to scenes in both generator and discriminator across image datasets.
-
Multiple-Identity Image Attacks Against Face-based Identity Verification
The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion realizing effective attacks that transfer across comparators.
-
Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning
Graph Laplacian interpolating activation replaces softmax in DNNs and improves natural accuracy, robust accuracy, and data efficiency.
-
Machine Reading Comprehension: a Literature Review
A 2019 survey of machine reading comprehension corpora and methods.