# Self-Adaptive Network Pruning

arXiv: https://arxiv.org/abs/1910.08906 · HTML: https://mlsanity.com/paper/1910.08906/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism](https://mlsanity.com/paper/2205.03055/) (2022)
- [Referring Expression Comprehension Using Language Adaptive Inference](https://mlsanity.com/paper/2306.04451/) (2023)
- [Energy-Latency Attacks: A New Adversarial Threat to Deep Learning](https://mlsanity.com/paper/2503.04963/) (2025)
- [Progressive Channel-Shrinking Network](https://mlsanity.com/paper/2304.00280/) (2023)
- [μ-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts](https://mlsanity.com/paper/2505.18451/) (2025)
- [DecisioNet: A Binary-Tree Structured Neural Network](https://mlsanity.com/paper/2207.01127/) (2022)

## Abstract (arXiv)

Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. In this paper, we propose to reduce such cost for CNNs through a self-adaptive network pruning method (SANP). Our method introduces a general Saliency-and-Pruning Module (SPM) for each convolutional layer, which learns to predict saliency scores and applies pruning for each channel. Given a total computation budget, SANP adaptively determines the pruning strategy with respect to each layer and each sample, such that the average computation cost meets the budget. This design allows SANP to be more efficient in computation, as well as more robust to datasets and backbones. Extensive experiments on 2 datasets and 3 backbones show that SANP surpasses state-of-the-art methods in both classification accuracy and pruning rate.