Striving for Simplicity: The All Convolutional Net

Code

• github.com/billyshin/CNN-Object-Recognition
  tf★ 1
• github.com/AlexSzen/wwf_shark_id
  pytorch★ 0
• github.com/imavijit/detect_it
  none★ 0
• github.com/BasileBron/Artificial-Intelligence-Lexical
  none★ 0
• github.com/hs2k/pytorch-smoothgrad
  pytorch★ 0
• github.com/axit54/Object-Recognition-using-the-All-CNN-network
  tf★ 0
• github.com/eclique/keras-gradcam
  tf★ 0
• github.com/balshersingh10/Object-Recognition
  none★ 0
• github.com/vpaliwal1/Image-Classification-using-CNN
  tf★ 0
• github.com/Paperspace/hyperopt-keras-sample
  tf★ 0

Abstract

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity of different components in the pipeline. We find that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Following this finding -- and building on other recent work for finding simple network structures -- we propose a new architecture that consists solely of convolutional layers and yields competitive or state of the art performance on several object recognition datasets (CIFAR-10, CIFAR-100, ImageNet). To analyze the network we introduce a new variant of the "deconvolution approach" for visualizing features learned by CNNs, which can be applied to a broader range of network structures than existing approaches.

Tasks

Benchmark Results

Reproductions