Hermosilla, Pedro; Schelling, Michael; Ritschel, Tobias; Ropinski, Timo; (2022) Variance-Aware Weight Initialization for Point Convolutional Neural Networks. In: Avidan, S and Brostow, G and Cisse, M and Farinella, GM and Hassner, T, (eds.) Computer Vision – ECCV 2022, PT XXVIII. (pp. pp. 74-89). Springer: Cham, Switzerland.

Preview

Text 2112.03777v2.pdf - Accepted Version Download (783kB) | Preview

Abstract

Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization by simply normalizing each layer based on batch statistics. Unfortunately, batch normalization has several drawbacks when applied to small batch sizes, as they are required to cope with memory limitations when learning on point clouds. While well-founded weight initialization strategies for regular convolutions can render batch normalization unnecessary and thus avoid its drawbacks, no such approaches have been proposed for point convolutional networks. To fill this gap, we propose a framework to unify the multitude of continuous convolutions. This enables our main contribution, variance-aware weight initialization. We show that this initialization can avoid batch normalization while achieving similar and, in some cases, better performance.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item