Learning Deep Features for Discriminative Localization

Global average pooling (GAP) polls the last convolutional features (activation map) into 1D vector X. The last fully connected layer, from X to logits, identifies the importance of each activation map, i.e. convolutional feature, to every class.
Class Activation Mapping: the predicted class score is mapped back to the previous convolutional layer to generate the class activation maps (CAMs). The CAM highlights the class-specific discriminative regions.
  1. Learning Deep Features for Discriminative Localization
  2. Github implementation

--

--

--

I write reviews on computer vision papers. Writing tips are welcomed.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Predicting High Risk Clients Using Machine Learning

Deep neural decision forest in keras

Decision forest and neural network integration

Introduction to Fourier analysis of time series

Animated circle synchronized with periodic function

Non-Stationarity and Memory In Financial Markets

Sorting Dating Profiles with Machine Learning and Python

Novelty Detection in Review Data

Machine Learning

Are you ready for NeurIPS 2018?

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Ahmed Taha

Ahmed Taha

I write reviews on computer vision papers. Writing tips are welcomed.

More from Medium

Emotional Computer Vision and Machine Consciousness

Review — Equalized Focal Loss for Dense Long-Tailed Object Detection

Expanding the Horizon, Real-World Application Library for Synthetically trained Neural Networks

Note down some statements about Deep Learning