blog.csdn

MMDetection 部署 ConvNeXt-V2：基于 FCMAE 预训练与 GRN 骨干的 Mask R-CNN 微调实战

本文以 MMDetection 仓库中 projects/ConvNeXt-V2子项目为核心，讲解如何将 ConvNeXt V2 全卷积掩码自编码器（FCMAE）预训练骨干接入 Mask R-CNN，完成 COCO 检测与实例分割任务的微调训练。读完本文，你将 ...
bilibili

PyTorch实战28-卷积自编码器(Convolutional Autoencoder)

被拒15次，创造PyTorch，Meta副总裁，Soumith Chintala——AI框架界的开山巨擘！他是深度学习框架PyTorch的联合创始人，更是将这 ...
innovationnewsnetwork

Autoencoder for anomaly detection in hperspectral imagery

Hyperspectral imaging (HSI) from spaceborne, airborne, and drone platforms has emerged as a transformative Earth observation technology and provides spatially distributed detailed spectral information ...
bilibili

PyTorch实战27-自编码器(Autoencoder)

【B站最全】清华大佬144集讲完的人工智能教程！从小白到学神！2025清华内部版人工智能入门基础，深度学习、机器学习、神经网络、OpenCV一口气学完！ 吹爆！这绝对是B站最好的人工智能入门 ...
techtimes

Korean Shipyard Deploys AI That Detects Robot Faults Without Failure Data

South Korean industrial AI company MakinaRocks has completed an anomaly detection system for welding robots at HD Korea Shipbuilding & Offshore Engineering (HD KSOE) that was trained entirely on data ...
quantumzeitgeist

Quantum Autoencoder Detects Time-Series Anomalies with Improved Reconstruction Accuracy

A bottleneck-based quantum convolutional autoencoder achieved a significant 17.2 per cent improvement in area under the receiver operating characteristic curve (AUC-ROC) when compared to architectures ...
GitHub

Unsupervised Detection of Underground Tunnels in Ground-Penetrating Radar Using Depth-Restricted Reconstruction Scoring

1. Denoising autoencoder trained on normal-only windows. Convolutional bottleneck architecture with a 256-D latent (64:1 compression, forces the network to keep only structural regularities of ...
Scientific Research Publishing

Zhang, M., Zeng, F., Yousif, M.Z., Zhu, Z., Lee, J.S. and Lim, H. (2025) Convolutional Autoencoder-Augmented Sparse Identification of Noisy Nonlinear Fluid Dynamics from ...

ABSTRACT: Sparse identification of nonlinear dynamical systems is an important project, directly addressing the physics community’s long-standing goal of data-driven discovery. Although many effective ...
jpt.spe

Autoencoders for Early Kick Detection: Improving Safety in Offshore Oilwell Drilling

This research addresses one of the most critical challenges in oilwell drilling: the early detection of kick anomalies. A kick anomaly is characterized by an undesirable influx of formation fluids ...