{"url":"/method/spade","slug":"spade","name":"SPADE","full_name":"Spatially-Adaptive Normalization","full_name_withheld":false,"description_markdown":"**SPADE**, or **Spatially-Adaptive Normalization** is a conditional normalization method for semantic image synthesis. Similar to [Batch Normalization](https://www.paperswithcode.com/method/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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","paper":"/paper/semantic-image-synthesis-with-spatially","first_author":"Taesung Park","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/semantic-image-synthesis-with-spatially"},"source":{"url":"https://arxiv.org/abs/1903.07291v2","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Normalization","url":"/methods/category/normalization","pwc_aliases":[]}],"n_papers_tagged":38,"archive_num_papers":38,"papers_newest_first":[{"paper":null,"title":"SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning","date":"2025-07-08","arxiv_id":"2507.05798","n_code_links":0,"syntology":null},{"paper":null,"title":"SPADE: Spectroscopic Photoacoustic Denoising using an Analytical and Data-free Enhancement Framework","date":"2024-12-16","arxiv_id":"2412.12068","n_code_links":0,"syntology":null},{"paper":null,"title":"$\\spadesuit$ SPADE $\\spadesuit$ Split Peak Attention DEcomposition","date":"2024-11-06","arxiv_id":"2411.05852","n_code_links":0,"syntology":null},{"paper":null,"title":"Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged Ventricles","date":"2024-11-02","arxiv_id":"2411.01351","n_code_links":0,"syntology":null},{"paper":null,"title":"SVS-GAN: Leveraging GANs for Semantic Video Synthesis","date":"2024-09-09","arxiv_id":"2409.06074","n_code_links":0,"syntology":null},{"paper":null,"title":"All-day Depth Completion","date":"2024-05-27","arxiv_id":"2405.17315","n_code_links":0,"syntology":null},{"paper":"/paper/towards-controllable-face-generation-with","title":"Controllable Face Synthesis with Semantic Latent Diffusion Models","date":"2024-03-19","arxiv_id":"2403.12743","n_code_links":2,"syntology":null},{"paper":"/paper/synthesizing-traffic-datasets-using-graph","title":"Synthesizing Traffic Datasets using Graph Neural Networks","date":"2023-12-08","arxiv_id":"2312.05031","n_code_links":1,"syntology":null},{"paper":"/paper/a-structured-pruning-algorithm-for-model","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","date":"2023-11-03","arxiv_id":"2311.02003","n_code_links":1,"syntology":null},{"paper":"/paper/spade-sparsity-guided-debugging-for-deep","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","date":"2023-10-06","arxiv_id":"2310.04519","n_code_links":1,"syntology":{"ran":5,"of":9,"unverified":4,"pointer_only":9}},{"paper":"/paper/semantic-image-synthesis-via-class-adaptive","title":"Semantic Image Synthesis via Class-Adaptive Cross-Attention","date":"2023-08-30","arxiv_id":"2308.16071","n_code_links":2,"syntology":null},{"paper":null,"title":"SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving","date":"2023-05-12","arxiv_id":"2305.07522","n_code_links":0,"syntology":null},{"paper":null,"title":"ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review","date":"2023-04-13","arxiv_id":"2305.03123","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-long-sequence-modeling-via-state","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","date":"2022-12-15","arxiv_id":"2212.08136","n_code_links":1,"syntology":{"ran":3,"of":5,"unverified":2,"pointer_only":0}},{"paper":null,"title":"SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch","date":"2022-11-30","arxiv_id":"2212.00173","n_code_links":0,"syntology":null},{"paper":null,"title":"Keep Your Friends Close & Enemies Farther: Debiasing Contrastive Learning with Spatial Priors in 3D Radiology Images","date":"2022-11-16","arxiv_id":"2211.08643","n_code_links":0,"syntology":null},{"paper":null,"title":"Synthesis of realistic fetal MRI with conditional Generative Adversarial Networks","date":"2022-09-20","arxiv_id":"2209.09696","n_code_links":0,"syntology":null},{"paper":"/paper/context-consistent-semantic-image-editing","title":"Context-Consistent Semantic Image Editing with Style-Preserved Modulation","date":"2022-07-13","arxiv_id":"2207.06252","n_code_links":1,"syntology":null},{"paper":null,"title":"MultiEarth 2022 -- The Champion Solution for Image-to-Image Translation Challenge via Generation Models","date":"2022-06-17","arxiv_id":"2207.00001","n_code_links":0,"syntology":null},{"paper":null,"title":"Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Coding","date":"2022-01-27","arxiv_id":"2201.11506","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-the-gap-between-label-and-reference-1","title":"Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation","date":"2021-10-11","arxiv_id":"2110.05055","n_code_links":1,"syntology":null},{"paper":"/paper/usis-unsupervised-semantic-image-synthesis","title":"USIS: Unsupervised Semantic Image Synthesis","date":"2021-09-29","arxiv_id":"2109.14715","n_code_links":1,"syntology":null},{"paper":null,"title":"3D Human Shape Style Transfer","date":"2021-09-03","arxiv_id":"2109.01587","n_code_links":0,"syntology":null},{"paper":null,"title":"UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing","date":"2021-08-12","arxiv_id":"2108.05650","n_code_links":0,"syntology":null},{"paper":"/paper/pd-gan-probabilistic-diverse-gan-for-image","title":"PD-GAN: Probabilistic Diverse GAN for Image Inpainting","date":"2021-05-05","arxiv_id":"2105.02201","n_code_links":1,"syntology":{"ran":1,"of":5,"unverified":4,"pointer_only":0}},{"paper":"/paper/deflocnet-deep-image-editing-via-flexible-low","title":"DeFLOCNet: Deep Image Editing via Flexible Low-level Controls","date":"2021-03-23","arxiv_id":"2103.12723","n_code_links":1,"syntology":{"ran":5,"of":9,"unverified":4,"pointer_only":0}},{"paper":"/paper/spade-a-spectral-method-for-black-box","title":"SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation","date":"2021-02-07","arxiv_id":"2102.03716","n_code_links":2,"syntology":null},{"paper":"/paper/focal-frequency-loss-for-generative-models","title":"Focal Frequency Loss for Image Reconstruction and Synthesis","date":"2020-12-23","arxiv_id":"2012.12821","n_code_links":1,"syntology":null},{"paper":"/paper/semantic-image-synthesis-via-efficient-class","title":"Efficient Semantic Image Synthesis via Class-Adaptive Normalization","date":"2020-12-08","arxiv_id":"2012.04644","n_code_links":1,"syntology":null},{"paper":null,"title":"Low Bandwidth Video-Chat Compression using Deep Generative Models","date":"2020-12-01","arxiv_id":"2012.00328","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":11},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":5},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":5},{"task":"/task/decoder","name":"Decoder","papers":4},{"task":"/task/translation","name":"Translation","papers":4},{"task":"/task/denoising","name":"Denoising","papers":3},{"task":"/task/super-resolution","name":"Super-Resolution","papers":3},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":2},{"task":"/task/attribute","name":"Attribute","papers":2},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":2},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/style-transfer","name":"Style Transfer","papers":2},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":1},{"task":"/task/3d-reconstruction","name":"3D Reconstruction","papers":1},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":1}],"tasks_shown":20,"n_tasks":68,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":3},{"year":"2020","papers":7},{"year":"2021","papers":7},{"year":"2022","papers":7},{"year":"2023","papers":6},{"year":"2024","papers":6},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/spade"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}