Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916267618729984 |
|---|---|
| author | Mitra, Pallavi Schwalbe, Gesina Klein, Nadja |
| author_facet | Mitra, Pallavi Schwalbe, Gesina Klein, Nadja |
| contents | Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. However, high computational and storage demands hinder their deployment into resource-constrained environments, such as embedded devices. Model pruning helps to meet these restrictions by reducing the model size, while maintaining superior performance. Meanwhile, safety-critical applications pose more than just resource and performance constraints. In particular, predictions must not be overly confident, i.e., provide properly calibrated uncertainty estimations (proper uncertainty calibration), and CNNs must be robust against corruptions like naturally occurring input perturbations (natural corruption robustness). This work investigates the important trade-off between uncertainty calibration, natural corruption robustness, and performance for current state-of-research post-hoc CNN pruning techniques in the context of image classification tasks. Our study reveals that post-hoc pruning substantially improves the model's uncertainty calibration, performance, and natural corruption robustness, sparking hope for safe and robust embedded CNNs.Furthermore, uncertainty calibration and natural corruption robustness are not mutually exclusive targets under pruning, as evidenced by the improved safety aspects obtained by post-hoc unstructured pruning with increasing compression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20876 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study Mitra, Pallavi Schwalbe, Gesina Klein, Nadja Computer Vision and Pattern Recognition Artificial Intelligence Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. However, high computational and storage demands hinder their deployment into resource-constrained environments, such as embedded devices. Model pruning helps to meet these restrictions by reducing the model size, while maintaining superior performance. Meanwhile, safety-critical applications pose more than just resource and performance constraints. In particular, predictions must not be overly confident, i.e., provide properly calibrated uncertainty estimations (proper uncertainty calibration), and CNNs must be robust against corruptions like naturally occurring input perturbations (natural corruption robustness). This work investigates the important trade-off between uncertainty calibration, natural corruption robustness, and performance for current state-of-research post-hoc CNN pruning techniques in the context of image classification tasks. Our study reveals that post-hoc pruning substantially improves the model's uncertainty calibration, performance, and natural corruption robustness, sparking hope for safe and robust embedded CNNs.Furthermore, uncertainty calibration and natural corruption robustness are not mutually exclusive targets under pruning, as evidenced by the improved safety aspects obtained by post-hoc unstructured pruning with increasing compression. |
| title | Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2405.20876 |