OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

21 Dec 2013Pierre SermanetDavid EigenXiang ZhangMichael MathieuRob FergusYann LeCun

We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Classification ImageNet OverFeat - 7 accurate models Top 1 Accuracy 66.04% # 146
Top 5 Accuracy 86.76% # 104

Methods used in the Paper