SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.02869 · ECCV · 2022

Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps

Shangqian Gao, Heng Huang, Alireza Ganjdanesh

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Convolutional Neural Networks (CNNs) compression is crucial to deploying these models in edge devices with limited resources. Existing channel pruning algorithms for CNNs have achieved plenty of success on complex models. They approach the pruning problem from various perspectives and use different metrics to guide the pruning process. However, these metrics mainly focus on the model's 'outputs' or 'weights' and neglect its 'interpretations' information. To fill in this gap, we propose to address the channel pruning problem from a novel perspective by leveraging the interpretations of a model to steer the pruning process, thereby utilizing information from both inputs and outputs of the model. However, existing interpretation methods cannot get deployed to achieve our goal as either they are inefficient for pruning or may predict non-coherent explanations. We tackle this challenge by introducing a selector model that predicts real-time smooth saliency masks for pruned models. We parameterize the distribution of explanatory masks by Radial Basis Function (RBF)-like functions to incorporate geometric prior of natural images in our selector model's inductive bias. Thus, we can obtain compact representations of explanations to reduce the computational costs of our pruning method. We leverage our selector model to steer the network pruning by maximizing the similarity of explanatory representations for the pruned and original models. Extensive experiments on CIFAR-10 and ImageNet benchmark datasets demonstrate the efficacy of our proposed method. Our implementations are available at https://github.com/Alii-Ganjj/InterpretationsSteeredPruning

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2209.02869")
get_code_for_paper("2209.02869")
have("2209.02869")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2209.02869.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2209.02869.svg)](https://syntology.ai/paper/2209.02869)

Connect an agent — have() is free.