Going Deeper with Convolutions

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed +4 more
9/17/2014
cs.CV

No official code found. Best implementation: dingchenwei/googLeNet (39 stars).

Abstract

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC 2014 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

View on arXivView PDF

Code Implementations(1)

dingchenwei/googLeNetCommunity25%

here is my implementation of the basic googLeNet describe in the paper "Going Deeper with Convolutions" in keras

3917

Similar Papers

FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction

85% match1 repo5432019

No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects

84% match1 repo2732022

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

84% match1 repo802016

KAN-Mixers: a new deep learning architecture for image classification

84% match2025

CondConv: Conditionally Parameterized Convolutions for Efficient Inference

83% match1 repo5.3k2019

Deep Pyramidal Residual Networks

83% match1 repo1312016

Cite this paper

@article{szegedy2014going,
  title  = {Going Deeper with Convolutions},
  author = {Christian Szegedy and Wei Liu and Yangqing Jia and Pierre Sermanet and Scott Reed and Dragomir Anguelov and Dumitru Erhan and Vincent Vanhoucke and Andrew Rabinovich},
  year   = {2014},
  eprint = {1409.4842},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1409.4842}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1409.4842.svg)](https://codeofpaper.com/paper/1409.4842)

Discussion