Multi-stage Adaptive Rank Statistic Pruning for Lightweight Human 3D Mesh Recovery Model
SCIE
SCOPUS
- Title
- Multi-stage Adaptive Rank Statistic Pruning for Lightweight Human 3D Mesh Recovery Model
- Authors
- Dong Hun Ryou; KIM, YOUWANG; Oh, Tae-Hyun
- Date Issued
- 2024-02
- Publisher
- Springer Verlag
- Abstract
- We present a rank statistic adaptive multi-stage pruning method to find lightweight neural networks for 3D human mesh recovery while minimizing accuracy drop. We observe that some feature maps often have prominent low-rank patterns regardless of input human images. Furthermore, even after pruning, feature channels that should have been pruned according to pruning criteria frequently re-appear in test time. From these observations, we design rank statistic adaptive multi-stage pruning; thereby, we can prune more filters with recovering mesh reconstruction accuracy. We demonstrate that, for DenseNet-121, 60.0% of parameters and 67.9% of FLOPs are saved while maintaining comparable accuracy to that of the original full model. This is a notable improvement compared to the competing method based on the L1 filter pruning, where the error is increased by 17.55% at the same pruning rate.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/116949
- DOI
- 10.1007/s00371-023-02798-x
- ISSN
- 0178-2789
- Article Type
- Article
- Citation
- Visual Computer, vol. 40, no. 2, page. 535 - 543, 2024-02
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.