# Zebra: Memory Bandwidth Reduction for CNN Accelerators With Zero Block Regularization of Activation Maps

Source: [Zebra: Memory Bandwidth Reduction for CNN Accelerators With Zero Block Regularization of Activation Maps](<https://www.sota2.com/research/paper/68fa6c7b1e209131cea34399>)

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

Data updated: 2025-10-26T00:11:46.889Z

Authors: Hsu-Tung Shih, Tian-Sheuan Chang

Published: 2022-05-02T09:57:17.000Z

## Abstract

The large amount of memory bandwidth between local buffer and external DRAM has become the speedup bottleneck of CNN hardware accelerators, especially for activation maps. To reduce memory bandwidth, we propose to learn pruning unimportant blocks dynamically with zero block regularization of activation maps (Zebra). This strategy has low computational overhead and could easily integrate with other pruning methods for better performance. The experimental results show that the proposed method can reduce 70\\% of memory bandwidth for Resnet-18 on Tiny-Imagenet within 1\\% accuracy drops and 2\\% accuracy gain with the combination of Network Slimming.

## 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.

- [Image Classification on TinyImageNet (test)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-test.md>): Image Classification; TinyImageNet (test); Accuracy: 61.46.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2205.00779>)

[PDF](<https://arxiv.org/pdf/2205.00779.pdf>)