U-Net

شبكة U-Net

بنية شبكة عصبية على شكل حرف U تتكون من مُرمِّز يُقلّص الأبعاد المكانية ومفكّ يُعيد تكبيرها مع وصلات تخطّي تربط الطبقات المتناظرة، وتُستخدم كهيكل أساسي لنموذج الانتشار.

A U-shaped neural network architecture with an encoder that reduces spatial dimensions and a decoder that restores them, with skip connections linking corresponding layers — used as the backbone for the diffusion model.

Also translated asبنية U-Net، شبكة يو-نت

First appears in this corpus in: Image-to-Image Translation with Conditional Adversarial Networks (2017)

Appears in these papers

Classifier-Free Diffusion Guidance2022 in the sky ✦
Denoising Diffusion Implicit Models2021 in the sky ✦
Denoising Diffusion Probabilistic Models2020 in the sky ✦
Diffusion Models Beat GANs on Image Synthesis2021 in the sky ✦
Flow Matching for Generative Modeling2023 in the sky ✦
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models2021 in the sky ✦
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding2022 in the sky ✦
High-Resolution Image Synthesis with Latent Diffusion Models2022 in the sky ✦
Image-to-Image Translation with Conditional Adversarial Networks2017 in the sky ✦
Image-to-Image Translation with Conditional Adversarial Networks2017 in the sky ✦
Generative Modeling by Estimating Gradients of the Data Distribution2019 in the sky ✦
Squeeze-and-Excitation Networks2018 in the sky ✦