FaceNet: A Unified Embedding for Face Recognition and Clustering

Embedding network objective is to keep (A,P) embedding closer than (A,N) embedding
  • I like the paper and enjoyed reading it.
  • In the paper, semi-hard negative selection process is not fully illustrated. Does the constraint relaxation means that random sampling will work?
  • The batch size used is 1800! if that's the number of triplets, This is big and might not be feasible on common GPUs. I am not sure how such big batch works for medium-size datasets?

--

--

--

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

Applying ML

Connecting a Machine Learning Model to a Web Dashboard using Flask and React

Neural Networks in Deep Learning and Image Classification

[Beginner] Linear Algebra (Point and Vector)

Using Deep Learning to infer Audio Genres using Images

Ensemble Learning

📈Linear Regression: Visualized 😇.

Face Detection Using OpenCV(Python)

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

Note down some statements about Deep Learning

An Introduction to Convolutional Neural Network (CNN)

Self-Supervised Learning: Representation Learning via Invariant Causal Mechanisms

What If The Systems Recommend Clothes For You To Purchase According To The Season?