# CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning

Source: [CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning](<https://www.sota2.com/research/paper/68fa72941e209131cea5747e>)

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

Data updated: 2025-10-26T02:29:52.311Z

Authors: Shivam Aggarwal, Kuluhan Binici, Tulika Mitra

Published: 2023-11-24T04:16:32.000Z

## Abstract

Machine learning pipelines for classification tasks often train a universal model to achieve accuracy across a broad range of classes. However, a typical user encounters only a limited selection of classes regularly. This disparity provides an opportunity to enhance computational efficiency by tailoring models to focus on user-specific classes. Existing works rely on unstructured pruning, which introduces randomly distributed non-zero values in the model, making it unsuitable for hardware acceleration. Alternatively, some approaches employ structured pruning, such as channel pruning, but these tend to provide only minimal compression and may lead to reduced model accuracy. In this work, we propose CRISP, a novel pruning framework leveraging a hybrid structured sparsity pattern that combines both fine-grained N:M structured sparsity and coarse-grained block sparsity. Our pruning strategy is guided by a gradient-based class-aware saliency score, allowing us to retain weights crucial for user-specific classes. CRISP achieves high accuracy with minimal memory consumption for popular models like ResNet-50, VGG-16, and MobileNetV2 on ImageNet and CIFAR-100 datasets. Moreover, CRISP delivers up to 14$\\times$ reduction in latency and energy consumption compared to existing pruning methods while maintaining comparable accuracy. Our code is available at https://github.com/shivmgg/CRISP/.

## 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/2311.14272>)

[PDF](<https://arxiv.org/pdf/2311.14272.pdf>)
