2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLSP-2.6
Paper Title Factorized CRF with batch normalization based on the entire training data
Authors Eran Goldman, Jacob Goldberger, Bar-Ilan University, Israel
SessionMLSP-2: Deep Learning Training Methods 2
LocationGather.Town
Session Time:Tuesday, 08 June, 13:00 - 13:45
Presentation Time:Tuesday, 08 June, 13:00 - 13:45
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Batch normalization (BN) is a key component of most neural network architectures. A major weakness of Batch Normalization is its critical dependence on having a reasonably large batch size, due to the inherent approximation of estimating the mean and variance with a single batch of data. Another weakness is the difficulty of applying BN in autoregressive or structured models. In this study we show that it is feasible to calculate the mean and variance using the entire training dataset instead of standard BN for any network node obtained as a linear function of the input features. We dub this method Full Batch Normalization (FBN). Our main focus is on a factorized autoregressive CRF model where we show that FBN is applicable, and allows for the integration of BN into the linear-chain CRF likelihood. The improved performance of FBN is illustrated on the huge SKU dataset that contains images of retail store product displays.