LGCVMLMay 12, 2019

Approximated Oracle Filter Pruning for Destructive CNN Width Optimization

arXiv:1905.04748v1137 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of deploying CNNs on computationally limited devices, but it is incremental as it builds on existing oracle pruning methods.

The paper tackles the problem of efficiently pruning filters in convolutional neural networks to reduce computational cost while maintaining accuracy, achieving negligible accuracy drop with acceptable time cost.

It is not easy to design and run Convolutional Neural Networks (CNNs) due to: 1) finding the optimal number of filters (i.e., the width) at each layer is tricky, given an architecture; and 2) the computational intensity of CNNs impedes the deployment on computationally limited devices. Oracle Pruning is designed to remove the unimportant filters from a well-trained CNN, which estimates the filters' importance by ablating them in turn and evaluating the model, thus delivers high accuracy but suffers from intolerable time complexity, and requires a given resulting width but cannot automatically find it. To address these problems, we propose Approximated Oracle Filter Pruning (AOFP), which keeps searching for the least important filters in a binary search manner, makes pruning attempts by masking out filters randomly, accumulates the resulting errors, and finetunes the model via a multi-path framework. As AOFP enables simultaneous pruning on multiple layers, we can prune an existing very deep CNN with acceptable time cost, negligible accuracy drop, and no heuristic knowledge, or re-design a model which exerts higher accuracy and faster inference.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes