{"url":"/method/activation-normalization","slug":"activation-normalization","name":"Activation Normalization","full_name":"Activation Normalization","full_name_withheld":false,"description_markdown":"**Activation Normalization** is a type of normalization used for flow-based generative models; specifically it was introduced in the [GLOW](https://paperswithcode.com/method/glow) architecture. An ActNorm layer performs an affine transformation of the activations using a scale and bias parameter per channel, similar to [batch normalization](https://paperswithcode.com/method/batch-normalization). These parameters are initialized such that the post-actnorm activations per-channel have zero mean and unit variance given an initial minibatch of data. This is a form of data dependent initilization. After initialization, the scale and bias are treated as regular trainable parameters that are independent of the data.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Glow: Generative Flow with Invertible 1x1 Convolutions","paper":"/paper/glow-generative-flow-with-invertible-1x1","first_author":"Diederik P. Kingma","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/glow-generative-flow-with-invertible-1x1"},"source":{"url":"http://arxiv.org/abs/1807.03039v2","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/openai/glow/blob/1f1352977cb1b21c7c0aa83b08efb24dfc216663/tfops.py#L70","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Normalization","url":"/methods/category/normalization","pwc_aliases":[]}],"n_papers_tagged":61,"archive_num_papers":61,"papers_newest_first":[{"paper":null,"title":"MARBLE: Material Recomposition and Blending in CLIP-Space","date":"2025-06-05","arxiv_id":"2506.05313","n_code_links":0,"syntology":null},{"paper":"/paper/promptvfx-text-driven-fields-for-open-world","title":"PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation","date":"2025-06-01","arxiv_id":"2506.01091","n_code_links":1,"syntology":null},{"paper":null,"title":"Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal","date":"2025-02-15","arxiv_id":"2502.10714","n_code_links":0,"syntology":null},{"paper":"/paper/glow-a-novel-flower-based-simulated-gossip","title":"GLow -- A Novel, Flower-Based Simulated Gossip Learning Strategy","date":"2025-01-15","arxiv_id":"2501.10463","n_code_links":1,"syntology":null},{"paper":null,"title":"Swarm Intelligence-Driven Client Selection for Federated Learning in Cybersecurity applications","date":"2024-11-28","arxiv_id":"2411.18877","n_code_links":0,"syntology":null},{"paper":"/paper/for-overall-nighttime-visibility-integrate","title":"For Overall Nighttime Visibility: Integrate Irregular Glow Removal With Glow-Aware Enhancement","date":"2024-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/super-monotonic-alignment-search","title":"Super Monotonic Alignment Search","date":"2024-09-12","arxiv_id":"2409.07704","n_code_links":1,"syntology":null},{"paper":null,"title":"Adaptative Context Normalization: A Boost for Deep Learning in Image Processing","date":"2024-09-07","arxiv_id":"2409.04759","n_code_links":0,"syntology":null},{"paper":"/paper/contextflow-generalist-specialist-flow-based","title":"ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding","date":"2024-06-02","arxiv_id":"2406.00578","n_code_links":1,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":4}},{"paper":null,"title":"Towards Greener Nights: Exploring AI-Driven Solutions for Light Pollution Management","date":"2024-04-15","arxiv_id":"2404.09453","n_code_links":0,"syntology":null},{"paper":null,"title":"Consumer Behavior under Benevolent Price Discrimination","date":"2024-04-04","arxiv_id":"2404.03581","n_code_links":0,"syntology":null},{"paper":"/paper/a-semi-supervised-nighttime-dehazing-baseline","title":"A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint","date":"2024-03-27","arxiv_id":"2403.18548","n_code_links":1,"syntology":{"ran":18,"of":24,"unverified":6,"pointer_only":24}},{"paper":null,"title":"NightHaze: Nighttime Image Dehazing via Self-Prior Learning","date":"2024-03-12","arxiv_id":"2403.07408","n_code_links":0,"syntology":null},{"paper":"/paper/an-attempt-to-generate-new-bridge-types-from-3","title":"An attempt to generate new bridge types from latent space of generative flow","date":"2024-01-18","arxiv_id":"2401.10299","n_code_links":1,"syntology":null},{"paper":null,"title":"Harnessing Density Ratios for Online Reinforcement Learning","date":"2024-01-18","arxiv_id":"2401.09681","n_code_links":0,"syntology":null},{"paper":null,"title":"NDELS: A Novel Approach for Nighttime Dehazing, Low-Light Enhancement, and Light Suppression","date":"2023-12-11","arxiv_id":"2312.06850","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-ligand-pose-sampling-for-molecular","title":"Enhancing Ligand Pose Sampling for Molecular Docking","date":"2023-11-30","arxiv_id":"2312.00191","n_code_links":1,"syntology":{"ran":1,"of":3,"unverified":2,"pointer_only":0}},{"paper":"/paper/from-generation-to-suppression-towards","title":"From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement","date":"2023-07-31","arxiv_id":"2307.16783","n_code_links":1,"syntology":null},{"paper":"/paper/stochastic-pitch-prediction-improves-the","title":"Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS","date":"2023-05-28","arxiv_id":"2305.17724","n_code_links":1,"syntology":null},{"paper":null,"title":"Generative Steganographic Flow","date":"2023-05-10","arxiv_id":"2305.05838","n_code_links":0,"syntology":null},{"paper":null,"title":"Tensor Slicing and Optimization for Multicore NPUs","date":"2023-04-06","arxiv_id":"2304.03013","n_code_links":0,"syntology":null},{"paper":null,"title":"ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus","date":"2023-02-28","arxiv_id":"2303.00069","n_code_links":0,"syntology":null},{"paper":null,"title":"GLOW: Global Layout Aware Attacks on Object Detection","date":"2023-02-27","arxiv_id":"2302.14166","n_code_links":0,"syntology":null},{"paper":"/paper/finc-flow-fast-and-invertible-k-times-k","title":"FInC Flow: Fast and Invertible $k \\times k$ Convolutions for Normalizing Flows","date":"2023-01-23","arxiv_id":"2301.09266","n_code_links":0,"syntology":null},{"paper":null,"title":"Local Differential Privacy Image Generation Using Flow-based Deep Generative Models","date":"2022-12-20","arxiv_id":"2212.10688","n_code_links":0,"syntology":null},{"paper":"/paper/domain-adaptation-with-adversarial-training-1","title":"Domain Adaptation with Adversarial Training on Penultimate Activations","date":"2022-08-26","arxiv_id":"2208.12853","n_code_links":1,"syntology":null},{"paper":"/paper/out-of-distribution-detection-via-frequency","title":"Out-of-distribution Detection via Frequency-regularized Generative Models","date":"2022-08-18","arxiv_id":"2208.09083","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":2}},{"paper":null,"title":"Implementation Of Tiny Machine Learning Models On Arduino 33 BLE For Gesture And Speech Recognition","date":"2022-07-23","arxiv_id":"2207.12866","n_code_links":0,"syntology":null},{"paper":null,"title":"GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion","date":"2022-07-04","arxiv_id":"2207.01454","n_code_links":0,"syntology":null},{"paper":null,"title":"Revisiting Over-Smoothness in Text to Speech","date":"2022-02-26","arxiv_id":"2202.13066","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":7},{"task":"/task/text-to-speech","name":"Text to Speech","papers":6},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":6},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":3},{"task":"/task/density-estimation","name":"Density Estimation","papers":3},{"task":"/task/flare-removal","name":"Flare Removal","papers":3},{"task":"/task/image-enhancement","name":"Image Enhancement","papers":3},{"task":"/task/ood-detection","name":"Out of Distribution (OOD) Detection","papers":3},{"task":"/task/unsupervised-anomaly-detection","name":"Unsupervised Anomaly Detection","papers":3},{"task":"/task/attribute","name":"Attribute","papers":2},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":2},{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":2},{"task":"/task/federated-learning","name":"Federated Learning","papers":2},{"task":"/task/image-dehazing","name":"Image Dehazing","papers":2},{"task":"/task/low-light-image-enhancement","name":"Low-Light Image Enhancement","papers":2},{"task":"/task/out-of-distribution-detection","name":"Out-of-Distribution Detection","papers":2},{"task":"/task/text-to-speech-synthesis","name":"Text-To-Speech Synthesis","papers":2},{"task":"/task/variational-inference","name":"Variational Inference","papers":2},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":2},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":1}],"tasks_shown":20,"n_tasks":86,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":9},{"year":"2020","papers":10},{"year":"2021","papers":11},{"year":"2022","papers":6},{"year":"2023","papers":9},{"year":"2024","papers":11},{"year":"2025","papers":4}],"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/activation-normalization"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}