On the Effect of Pre-Processing and Model Complexity for Plastic
Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging
- URL: http://arxiv.org/abs/2203.11209v1
- Date: Mon, 21 Mar 2022 11:19:11 GMT
- Title: On the Effect of Pre-Processing and Model Complexity for Plastic
Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging
- Authors: Klaas Dijkstra, Maya Aghaei, Femke Jaarsma, Martin Dijkstra, Rudy
Folkersma, Jan Jager, Jaap van de Loosdrecht
- Abstract summary: Computer vision and deep learning enable automated analysis of short-wave-infrared hyper-spectral images of plastics.
In this paper, we show the importance of efficient model selection for resolving the task of hyper-spectral image segmentation.
We introduce the largest, most versatile hyper-spectral dataset of plastic flakes of four primary polymer types.
- Score: 0.11083289076967892
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The importance of plastic waste recycling is undeniable. In this respect,
computer vision and deep learning enable solutions through the automated
analysis of short-wave-infrared hyper-spectral images of plastics. In this
paper, we offer an exhaustive empirical study to show the importance of
efficient model selection for resolving the task of hyper-spectral image
segmentation of various plastic flakes using deep learning. We assess the
complexity level of generic and specialized models and infer their performance
capacity: generic models are often unnecessarily complex. We introduce two
variants of a specialized hyper-spectral architecture, PlasticNet, that
outperforms several well-known segmentation architectures in both performance
as well as computational complexity. In addition, we shed lights on the
significance of signal pre-processing within the realm of hyper-spectral
imaging. To complete our contribution, we introduce the largest, most versatile
hyper-spectral dataset of plastic flakes of four primary polymer types.
Related papers
- UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks [36.61645124563195]
We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions.
We use semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution images.
Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images.
arXiv Detail & Related papers (2024-07-02T11:02:19Z) - Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning [49.197385954021456]
In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for visualization and subsequent analysis tasks.
To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated.
Most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios.
arXiv Detail & Related papers (2024-06-10T02:20:26Z) - Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models [48.87160158792048]
We introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way.
Experiments on a public high-resolution OCT dataset show that our synthetic data have realistic high-resolution and global features, surpassing the capabilities of existing methods.
arXiv Detail & Related papers (2024-05-26T10:58:22Z) - PLASTIC: Improving Input and Label Plasticity for Sample Efficient
Reinforcement Learning [54.409634256153154]
In Reinforcement Learning (RL), enhancing sample efficiency is crucial.
In principle, off-policy RL algorithms can improve sample efficiency by allowing multiple updates per environment interaction.
Our study investigates the underlying causes of this phenomenon by dividing plasticity into two aspects.
arXiv Detail & Related papers (2023-06-19T06:14:51Z) - GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from
Multi-view Images [79.39247661907397]
We introduce an effective framework Generalizable Model-based Neural Radiance Fields to synthesize free-viewpoint images.
Specifically, we propose a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy.
arXiv Detail & Related papers (2023-03-24T03:32:02Z) - Real-time Hyperspectral Imaging in Hardware via Trained Metasurface
Encoders [55.16861072631285]
Hyperspectral imaging has attracted significant attention to identify spectral signatures for image classification and automated pattern recognition in computer vision.
This work introduces Hyplex, a new integrated architecture addressing the limitations discussed above.
Hyplex is a CMOS-compatible, fast hyperspectral camera that replaces bulk optics with nanoscale metasurfaces inversely designed through artificial intelligence.
arXiv Detail & Related papers (2022-04-05T09:52:51Z) - Interpretable Hyperspectral AI: When Non-Convex Modeling meets
Hyperspectral Remote Sensing [57.52865154829273]
Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience remote sensing (RS)
In the past decade efforts have been made to process analyze these hyperspectral (HS) products mainly by means of seasoned experts.
For this reason, it is urgent to develop more intelligent and automatic approaches for various HS RS applications.
arXiv Detail & Related papers (2021-03-02T03:32:10Z) - Unveiling the role of plasticity rules in reservoir computing [0.0]
Reservoir Computing (RC) is an appealing approach in Machine Learning.
We analyze the role that plasticity rules play on the changes that lead to a better performance of RC.
arXiv Detail & Related papers (2021-01-14T19:55:30Z) - Active learning of deep surrogates for PDEs: Application to metasurface
design [30.731619528075214]
We present an active learning algorithm that reduces the number of training points by more than an order of magnitude for a neural-network surrogate model of optical-surface components.
Results show that the surrogate evaluation is over two orders of magnitude faster than a direct solve, and we demonstrate how this can be exploited to accelerate large-scale engineering optimization.
arXiv Detail & Related papers (2020-08-24T17:14:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.