Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
This work addresses the need for more efficient neural network design for researchers and practitioners, though it is incremental as it builds on existing pruning and architecture search methods.
The paper tackles the problem of designing computationally efficient neural networks by introducing a framework called network adjustment, which iteratively adjusts channel counts per layer based on FLOPs utilization ratio, resulting in consistent outperformance over pruning methods on standard image classification datasets.
Automatic designing computationally efficient neural networks has received much attention in recent years. Existing approaches either utilize network pruning or leverage the network architecture search methods. This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs, so that under each network configuration, one can estimate the FLOPs utilization ratio (FUR) for each layer and use it to determine whether to increase or decrease the number of channels on the layer. Note that FUR, like the gradient of a non-linear function, is accurate only in a small neighborhood of the current network. Hence, we design an iterative mechanism so that the initial network undergoes a number of steps, each of which has a small `adjusting rate' to control the changes to the network. The computational overhead of the entire search process is reasonable, i.e., comparable to that of re-training the final model from scratch. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach, which consistently outperforms the pruning counterpart. The code is available at https://github.com/danczs/NetworkAdjustment.