Learning Accurate Performance Predictors for Ultrafast Automated Model Compression

In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely search the desirable compression policy based on the accuracy from exhaustively trained lightweight models, and existing di...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer vision Jg. 131; H. 7; S. 1761 - 1783
Hauptverfasser: Wang, Ziwei, Lu, Jiwen, Xiao, Han, Liu, Shengyu, Zhou, Jie
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.07.2023
Springer
Springer Nature B.V
Schlagworte:
Accuracy
Artificial Intelligence
Automation
Complexity
Computational efficiency
Computer Imaging
Computer Science
Computing costs
Image classification
Image compression
Image Processing and Computer Vision
Object recognition
Optimization
Pattern Recognition
Pattern Recognition and Graphics
Performance prediction
Searching
Vision
Compression policy optimization
Performance predictor
Evolutionary search
Uncertainty estimation
Automated model compression
ISSN:0920-5691, 1573-1405
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely search the desirable compression policy based on the accuracy from exhaustively trained lightweight models, and existing differentiable methods optimize an extremely large supernet to obtain the required compressed model for deployment. They both cause heavy computational cost due to the complex compression policy search and evaluation process. On the contrary, we obtain the optimal efficient networks by directly optimizing the compression policy with an accurate performance predictor, where the ultrafast automated model compression for various computational cost constraint is achieved without complex compression policy search and evaluation. Specifically, we first train the performance predictor based on the accuracy from uncertain compression policies actively selected by efficient evolutionary search, so that informative supervision is provided to learn the accurate performance predictor with acceptable cost. Then we leverage the gradient that maximizes the predicted performance under the barrier complexity constraint for ultrafast acquisition of the desirable compression policy, where adaptive update stepsizes with momentum are employed to enhance optimality of the acquired pruning and quantization strategy. Compared with the state-of-the-art automated model compression methods, experimental results on image classification and object detection show that our method achieves competitive accuracy-complexity trade-offs with significant reduction of the search cost. Code is available at https://github.com/ZiweiWangTHU/SeerNet .
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-023-01783-0