Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM
This work addresses the high computational costs of deep models for scenarios with limited memory or computational resources, representing an incremental improvement in compression techniques.
The paper tackles the problem of compressing deep learning models for deployment in resource-limited scenarios by representing network weights with extremely low bits, achieving more effective compression and acceleration than state-of-the-art methods in experiments on image recognition and object detection.
Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on compressing and accelerating deep models with network weights represented by very small numbers of bits, referred to as extremely low bit neural network. We model this problem as a discretely constrained optimization problem. Borrowing the idea from Alternating Direction Method of Multipliers (ADMM), we decouple the continuous parameters from the discrete constraints of network, and cast the original hard problem into several subproblems. We propose to solve these subproblems using extragradient and iterative quantization algorithms that lead to considerably faster convergency compared to conventional optimization methods. Extensive experiments on image recognition and object detection verify that the proposed algorithm is more effective than state-of-the-art approaches when coming to extremely low bit neural network.