Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
read the original abstract
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low computational cost. Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. This raises the question of whether there are any benefit in combining the Inception architecture with residual connections. Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly. There is also some evidence of residual Inception networks outperforming similarly expensive Inception networks without residual connections by a thin margin. We also present several new streamlined architectures for both residual and non-residual Inception networks. These variations improve the single-frame recognition performance on the ILSVRC 2012 classification task significantly. We further demonstrate how proper activation scaling stabilizes the training of very wide residual Inception networks. With an ensemble of three residual and one Inception-v4, we achieve 3.08 percent top-5 error on the test set of the ImageNet classification (CLS) challenge
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Deep Variational Information Bottleneck
Deep VIB is a neural-network parameterization of the information bottleneck objective trained via variational inference and the reparameterization trick, yielding improved generalization and adversarial robustness.
-
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MobileNets introduce depthwise separable convolutions plus width and resolution multipliers to produce efficient CNNs that trade off latency and accuracy for mobile and embedded vision applications.
-
Wide Residual Networks
Wide residual networks achieve higher accuracy and faster training than very deep thin residual networks by increasing width and decreasing depth, setting new state-of-the-art results on CIFAR, SVHN, and ImageNet.
-
Personalized Face Privacy Protection From a Single Image
FaceCloak learns a lightweight identity-specific cloaking mask from a single image via synthetic face generation and iterative embedding perturbation to evade multiple recognition models.
-
Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
A cGAN method with edge-filtered combined inputs generates synthetic polyp images from normal colonoscopy frames to augment training data and improve detection performance.
-
New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms
Replacing pointwise convolutions with DWHT yields a model with 79.1% fewer parameters, 48.4% fewer FLOPs, and 1.49% higher accuracy than MobileNet-V1 on CIFAR-100.
-
Lung Nodules Detection and Segmentation Using 3D Mask-RCNN
Adapted Mask-RCNN to 3D and applied it to lung nodule detection and segmentation on CT scans, reporting competitive detection results on the LUNA16 dataset.
-
Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches
Region-based deep CNN with transfer learning and post-learning methods achieves better polyp detection performance than prior systems on large colonoscopy image and video databases.
-
Measuring the Transferability of Adversarial Examples
Empirical measurement of adversarial example transferability between VGG and Inception model classes with methodological refinements to attack strength selection, perturbation clipping, and evaluation via SSIM.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.