A Proper Orthogonal Decomposition approach for parameters reduction of Single Shot Detector networks
As a major breakthrough in artificial intelligence and deep learning, Convolutional Neural Networks have achieved an impressive success in solving many problems in several fields including computer vision and image processing. Real-time performance, robustness of algorithms and fast training processes remain open problems in these contexts. In addition object recognition and detection are challenging tasks for resource-constrained embedded systems, commonly used in the industrial sector. To overcome these issues, we propose a dimensionality reduction framework based on Proper Orthogonal Decomposition, a classical model order reduction technique, in order to gain a reduction in the number of hyperparameters of the net. We have applied such framework to SSD300 architecture using PASCAL VOC dataset, demonstrating a reduction of the network dimension and a remarkable speedup in the fine-tuning of the network in a transfer learning context.
Code (0)
등록된 구현이 없습니다.
Tasks
Dimensionality ReductionObject RecognitionTransfer LearningSimilar Papers 제목 키워드 기반
RESEARCH PAPER Crack identification using model reduction based on proper orthogonal decomposition coupled with radial basis functions
This work deals with the crack identification using model reduction based on the proper orthogonal decomposition method. The proposed inverse problem consists of the estimation of the crack length and its position in a p…
PositionSparsifying dimensionality reduction of PDE solution data with Bregman learning
Classical model reduction techniques project the governing equations onto a linear subspace of the original state space. More recent data-driven techniques use neural networks to enable nonlinear projections. Whilst thos…
compressed sensingDecoderDimensionality ReductionModel Order Reduction based on Runge-Kutta Neural Network
Model Order Reduction (MOR) methods enable the generation of real-time-capable digital twins, which can enable various novel value streams in industry. While traditional projection-based methods are robust and accurate f…
Dimensionality ReductionPOD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
Deep learning-based reduced order models (DL-ROMs) have been recently proposed to overcome common limitations shared by conventional reduced order models (ROMs) - built, e.g., through proper orthogonal decomposition (POD…
Dimensionality ReductionNonlinear proper orthogonal decomposition for convection-dominated flows
Autoencoder techniques find increasingly common use in reduced order modeling as a means to create a latent space. This reduced order representation offers a modular data-driven modeling approach for nonlinear dynamical …
Time SeriesTime Series Analysis