# BRIEF: Backward Reduction of CNNs with Information Flow Analysis

Source: [BRIEF: Backward Reduction of CNNs with Information Flow Analysis](<https://www.sota2.com/research/paper/68fa65021e209131cea07d86>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:16:52.800Z

Authors: Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang

Published: 2018-07-16T08:32:54.000Z

## Abstract

This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we can achieve additional 10.81% and 37.56% reduction, respectively, with negligible performance degradation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1807.05726>)

[PDF](<https://arxiv.org/pdf/1807.05726.pdf>)