Pith. sign in

REVIEW

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.14306 v2 pith:LNNQP7PB submitted 2023-06-25 cs.LG cs.CV

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks

classification cs.LG cs.CV
keywords pruningrobustnessadasaprobustadaptivecompactnesscompressiongoals
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains, while the process of compression exploits specificity in one domain. We introduce Adaptive Sharpness-Aware Pruning (AdaSAP), which unifies these goals through the lens of network sharpness. The AdaSAP method produces sparse networks that are robust to input variations which are unseen at training time. We achieve this by strategically incorporating weight perturbations in order to optimize the loss landscape. This allows the model to be both primed for pruning and regularized for improved robustness. AdaSAP improves the robust accuracy of pruned models on image classification by up to +6% on ImageNet C and +4% on ImageNet V2, and on object detection by +4% on a corrupted Pascal VOC dataset, over a wide range of compression ratios, pruning criteria, and network architectures, outperforming recent pruning art by large margins.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.