Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SPADE

Spatially-Adaptive Normalization

GeneralIntroduced 200038 papers

Description

SPADE, or Spatially-Adaptive Normalization is a conditional normalization method for semantic image synthesis. Similar to Batch Normalization, the activation is normalized in the channel-wise manner and then modulated with learned scale and bias. In the SPADE, the mask is first projected onto an embedding space and then convolved to produce the modulation parameters $\gamma$ and $\beta .$ Unlike prior conditional normalization methods, $\gamma$ and $\mathbf{\beta}$ are not vectors, but tensors with spatial dimensions. The produced $\gamma$ and $\mathbf{\beta}$ are multiplied and added to the normalized activation element-wise.

Papers Using This Method

SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning2025-07-08 SPADE: Spectroscopic Photoacoustic Denoising using an Analytical and Data-free Enhancement Framework2024-12-16 $\spadesuit$ SPADE $\spadesuit$ Split Peak Attention DEcomposition2024-11-06 Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged Ventricles2024-11-02 SVS-GAN: Leveraging GANs for Semantic Video Synthesis2024-09-09 All-day Depth Completion2024-05-27 Controllable Face Synthesis with Semantic Latent Diffusion Models2024-03-19 Synthesizing Traffic Datasets using Graph Neural Networks2023-12-08 Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning2023-11-03 SPADE: Sparsity-Guided Debugging for Deep Neural Networks2023-10-06 Semantic Image Synthesis via Class-Adaptive Cross-Attention2023-08-30 SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving2023-05-12 ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review2023-04-13 Efficient Long Sequence Modeling via State Space Augmented Transformer2022-12-15 SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch2022-11-30 Keep Your Friends Close & Enemies Farther: Debiasing Contrastive Learning with Spatial Priors in 3D Radiology Images2022-11-16 Synthesis of realistic fetal MRI with conditional Generative Adversarial Networks2022-09-20 Context-Consistent Semantic Image Editing with Style-Preserved Modulation2022-07-13 MultiEarth 2022 -- The Champion Solution for Image-to-Image Translation Challenge via Generation Models2022-06-17 Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Coding2022-01-27