Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models

• URL: http://arxiv.org/abs/2409.03901v2
• Date: Mon, 21 Oct 2024 23:15:51 GMT
• Title: Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models
• Authors: Thanh-Dung Le, Vu Nguyen Ha, Ti Ti Nguyen, Geoffrey Eappen, Prabhu Thiruvasagam, Luis M. Garces-Socarras, Hong-fu Chou, Jorge L. Gonzalez-Rios, Juan Carlos Merlano-Duncan, Symeon Chatzinotas,
• Abstract summary: This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing. We compare the performance of traditional CNN-based, ResNet-based, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Vision Transformer models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in terms of accuracy and efficiency.
• Score: 28.69148416385582
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against noisy data conditions commonly encountered during satellite-based inference. Through extensive experimentation, we compare the performance of traditional CNN-based, ResNet-based, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Vision Transformer (ViT) models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in terms of accuracy and efficiency. These models achieve high performance with reduced computational requirements and exhibit greater resilience during inference under noisy conditions. While MobileViTV2 has excelled on clean validation data, EfficientViT-M2 has proved more robust when handling noise, making it the most suitable model for onboard satellite EO tasks. Our experimental results demonstrate that EfficientViT-M2 is the optimal choice for reliable and efficient RS-IC in satellite operations, achieving 98.76 % of accuracy, precision, and recall. Precisely, EfficientViT-M2 delivers the highest performance across all metrics, excels in training efficiency (1,000s) and inference time (10s), and demonstrates greater robustness (overall robustness score of 0.79). Consequently, EfficientViT-M2 consumes 63.93 % less power than MobileViTV2 (79.23 W) and 73.26 % less power than SwinTransformer (108.90 W). This highlights its significant advantage in energy efficiency.

Related papers

• Vision-based autonomous structural damage detection using data-driven methods [0.0]
  This study addresses the need for efficient and accurate damage detection in wind turbine structures. Traditional inspection methods, such as manual assessments and non-destructive testing (NDT), are often costly, time-consuming, and prone to human error. To tackle these challenges, this research investigates advanced deep learning algorithms for vision-based structural health monitoring.
  arXiv  Detail & Related papers  (2025-01-28T02:52:04Z)
• Real-time Monitoring of Lower Limb Movement Resistance Based on Deep Learning [0.0]
  Real-time lower limb movement resistance monitoring is critical for various applications in clinical and sports settings, such as rehabilitation and athletic training. We propose a novel Mobile Multi-Task Learning Network (MMTL-Net) that integrates MobileNetV3 for efficient feature extraction and employs multi-task learning to simultaneously predict resistance levels and recognize activities. The advantages of MMTL-Net include enhanced accuracy, reduced latency, and improved computational efficiency, making it highly suitable for real-time applications.
  arXiv  Detail & Related papers  (2024-10-13T18:19:48Z)
• An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training [51.622652121580394]
  Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the textitextremely simple lightweight ViTs' fine-tuning performance can also benefit from this pre-training paradigm. Our pre-training with distillation on pure lightweight ViTs with vanilla/hierarchical design ($5.7M$/$6.5M$) can achieve $79.4%$/$78.9%$ top-1 accuracy on ImageNet-1
  arXiv  Detail & Related papers  (2024-04-18T14:14:44Z)
• Efficient Modulation for Vision Networks [122.1051910402034]
  We propose efficient modulation, a novel design for efficient vision networks. We demonstrate that the modulation mechanism is particularly well suited for efficient networks. Our network can accomplish better trade-offs between accuracy and efficiency.
  arXiv  Detail & Related papers  (2024-03-29T03:48:35Z)
• FMViT: A multiple-frequency mixing Vision Transformer [17.609263967586926]
  We propose an efficient hybrid ViT architecture named FMViT. This approach blends high-frequency features and low-frequency features with varying frequencies, enabling it to capture both local and global information effectively. We demonstrate that FMViT surpasses existing CNNs, ViTs, and CNNTransformer hybrid architectures in terms of latency/accuracy trade-offs for various vision tasks.
  arXiv  Detail & Related papers  (2023-11-09T19:33:50Z)
• E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [55.50908600818483]
  Fine-tuning large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. We propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation. Our approach outperforms several state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T19:03:21Z)
• EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention [44.148667664413004]
  We propose a family of high-speed vision transformers named EfficientViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations. To address this, we present a cascaded group attention module feeding attention heads with different splits.
  arXiv  Detail & Related papers  (2023-05-11T17:59:41Z)
• Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [56.87383229709899]
  We develop an information rectification module (IRM) and a distribution guided distillation scheme for fully quantized vision transformers (Q-ViT) Our method achieves a much better performance than the prior arts.
  arXiv  Detail & Related papers  (2022-10-13T04:00:29Z)
• Supervised Machine Learning for Effective Missile Launch Based on Beyond Visual Range Air Combat Simulations [0.19573380763700707]
  We use resampling techniques to improve the predictive model, analyzing accuracy, precision, recall, and f1-score. The models with the best f1-score brought values of 0.379 and 0.465 without and with the resampling technique, respectively, which is an increase of 22.69%. It is possible to develop decision support tools based on machine learning models, which may improve the flight quality in BVR air combat.
  arXiv  Detail & Related papers  (2022-07-09T04:06:00Z)
• Improving Vision Transformers by Revisiting High-frequency Components [106.7140968644414]
  We show that Vision Transformer (ViT) models are less effective in capturing the high-frequency components of images than CNN models. To compensate, we propose HAT, which directly augments high-frequency components of images via adversarial training. We show that HAT can consistently boost the performance of various ViT models.
  arXiv  Detail & Related papers  (2022-04-03T05:16:51Z)
• When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [111.44860506703307]
  Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures. This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference. We show that the improved robustness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
  arXiv  Detail & Related papers  (2021-06-03T02:08:03Z)

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.