Going Deeper with Convolutions

CVPR 2015 Christian SzegedyWei LiuYangqing JiaPierre SermanetScott ReedDragomir AnguelovDumitru ErhanVincent VanhouckeAndrew Rabinovich

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... (read more)

PDF Abstract CVPR 2015 PDF CVPR 2015 Abstract

Code


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet Inception V1 Top 1 Accuracy 69.8% # 142
Top 5 Accuracy 89.9% # 95
Number of params 5M # 69

Methods used in the Paper