# Toward domain generalized pruning by scoring out-of-distribution importance

arXiv: https://arxiv.org/abs/2210.13810 · HTML: https://mlsanity.com/paper/2210.13810/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Improve Unsupervised Domain Adaptation with Mixup Training](https://mlsanity.com/paper/2001.00677/) (2020)
- [Neural Pruning via Growing Regularization](https://mlsanity.com/paper/2012.09243/) (2020)
- [ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting](https://mlsanity.com/paper/2007.03260/) (2020)
- [Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy](https://mlsanity.com/paper/2103.03014/) (2021)
- [Neuron Coverage-Guided Domain Generalization](https://mlsanity.com/paper/2103.00229/) (2021)
- [Channel Pruning Guided by Classification Loss and Feature Importance](https://mlsanity.com/paper/2003.06757/) (2020)
- [ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression](https://mlsanity.com/paper/2006.04127/) (2020)
- [Structural Compression of Convolutional Neural Networks](https://mlsanity.com/paper/1705.07356/) (2017)

## Built on by (most cited first, 1 of 1)

- [Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking](https://mlsanity.com/paper/2608.08624/) (2026)

## Abstract (arXiv)

Filter pruning has been widely used for compressing convolutional neural networks to reduce computation costs during the deployment stage. Recent studies have shown that filter pruning techniques can achieve lossless compression of deep neural networks, reducing redundant filters (kernels) without sacrificing accuracy performance. However, the evaluation is done when the training and testing data are from similar environmental conditions (independent and identically distributed), and how the filter pruning techniques would affect the cross-domain generalization (out-of-distribution) performance is largely ignored. We conduct extensive empirical experiments and reveal that although the intra-domain performance could be maintained after filter pruning, the cross-domain performance will decay to a large extent. As scoring a filter's importance is one of the central problems for pruning, we design the importance scoring estimation by using the variance of domain-level risks to consider the pruning risk in the unseen distribution. As such, we can remain more domain generalized filters. The experiments show that under the same pruning ratio, our method can achieve significantly better cross-domain generalization performance than the baseline filter pruning method. For the first attempt, our work sheds light on the joint problem of domain generalization and filter pruning research.