BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference

Abstract

Long Short-Term Memory (LSTM) and 3D convolution (Conv3D) show impressive results for many video-based applications but require large memory and intensive computing. Motivated by recent works on hardware-algorithmic co-design towards efficient inference, we propose a compact binarized Conv3D-LSTM model architecture called BILLNET, compatible with a highly resource-constrained hardware. Firstly, BILLNET proposes to factorize the costly standard Conv3D by two pointwise convolutions with a grouped convolution in-between. Secondly, BILLNET enables binarized weights and activations via a MUX-OR-gated residual architecture. Finally, to efficiently train BILLNET, we propose a multi-stage training strategy enabling to fully quantize LSTM layers. Results on Jester dataset show that our method can obtain high accuracy with extremely low memory and computational budgets compared to existing Conv3D resource-efficient models.

Published at IEEE SiPS 2022

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Ternary Weight Networks
• Recurrent Neural Networks With Limited Numerical Precision
• Revisiting 3D ResNets for Video Recognition