Tagged articles
U-Net
10 articles · Page 1 of 1
This article introduces the U‑Net architecture—originally designed for medical image segmentation—explains why its pixel‑wise processing makes it the core denoising engine in Stable Diffusion, details three key modifications for diffusion models, and walks through a ResNet‑50‑based implementation trained on the VOC2012 dataset, achieving 0.92 pixel accuracy and 0.64 mean IoU.
PyTorchResNet50Stable Diffusion
0 likes · 11 min read

DeepFusion combines radar, historical precipitation, numerical weather prediction, and terrain data through independent encoders and attention‑based multi‑scale fusion, achieving high‑resolution 0‑2 hour heavy‑rain forecasts and demonstrating the benefits of multi‑modal deep learning for short‑term precipitation prediction.
Attention MechanismDeepFusionNWP
0 likes · 13 min read

DeepMind’s AlphaGenome, showcased on Nature’s cover, processes 1 Mb DNA sequences at single‑base resolution to predict thousands of regulatory attributes across cell types, using a U‑Net‑style architecture and two‑stage pre‑training plus distillation, achieving state‑of‑the‑art performance on 24 benchmarks and delivering variant‑effect scores in under one second on an H100 GPU.
AlphaGenomeDeepMindU-Net
0 likes · 11 min read

A recent MIT‑Toyota study shows that the locality observed in image diffusion models emerges from the statistical structure of training data rather than from architectural biases, and a simple linear denoiser can replicate this behavior, reshaping how we think about model design.
Data StatisticsImage GenerationU-Net
0 likes · 10 min read

This article explains the fundamental principles of diffusion models, using physics and machine‑learning analogies to describe forward and reverse diffusion, the role of Gaussian noise, iteration trade‑offs, U‑Net architecture, and shared‑weight training for image generation.
Generative AIImage GenerationU-Net
0 likes · 8 min read

This tutorial walks through implementing a basic Denoising Diffusion Probabilistic Model in Python, explaining the forward noise schedule, reverse denoising training, and providing complete code for noise schedules, diffusion functions, residual and attention blocks, a UNet architecture, loss computation, and a training loop.
AttentionDDPMPython
0 likes · 26 min read

The article examines the challenge of out‑of‑vocabulary terms in Chinese e‑commerce NLP, reviews classic unsupervised metrics such as frequency, cohesion and neighbor entropy, and proposes a lightweight fully‑convolutional network inspired by image‑segmentation techniques to automatically detect new words.
CNNNLPNew Word Discovery
0 likes · 10 min read


JD TechJun 12, 2021 · Artificial Intelligence
The paper presents DeepDualMapper, a gated‑fusion deep network that combines aerial imagery and vehicle trajectory data to automatically generate high‑precision maps, detailing its architecture, gated and refinement modules, and experimental validation on three city datasets.
Trajectory DataU-Netaerial imagery
0 likes · 7 min read


Amap TechMar 23, 2020 · Artificial Intelligence
Gaode leverages high‑resolution satellite imagery as an active discovery tool for map updates, extracting road, region and building elements through advanced semantic segmentation networks (U‑Net, ASPP, attention, non‑local) and instance‑segmentation pipelines, to accelerate accurate road‑network and building‑block data refreshes while addressing future scalability challenges.
Computer VisionSatellite ImageryU-Net
0 likes · 11 min read

This article explores the challenges of OCR on warped document images, reviews traditional and deep‑learning‑based correction methods, describes a synthetic dataset generation pipeline, proposes enhanced U‑Net architectures including stacked and dilated variants, evaluates them with MS‑SSIM, and outlines future research directions.
Dilated ConvolutionOCRU-Net
0 likes · 18 min read
