{"url":"/method/nice","slug":"nice","name":"NICE","full_name":"Non-linear Independent Component Estimation","full_name_withheld":false,"description_markdown":"**NICE**, or **Non-Linear Independent Components Estimation** is a framework for modeling complex high-dimensional densities. It is based on the idea that a good representation is one in which the data has a distribution that is easy to model. For this purpose, a non-linear deterministic transformation of the data is learned that maps it to a latent space so as to make the transformed data conform to a factorized distribution, i.e., resulting in independent latent variables.  The transformation is parameterised so that computing the determinant of the Jacobian and inverse Jacobian is trivial, yet it maintains the ability to learn complex non-linear transformations, via a composition of simple building blocks, each based on a deep neural network. The training criterion is simply the exact log-likelihood. The transformation used in NICE is the [affine coupling](https://paperswithcode.com/method/affine-coupling) layer without the scale term, known as additive coupling layer:\r\n\r\n$$ y\\_{I\\_{2}} = x\\_{I\\_{2}} + m\\left(x\\_{I\\_{1}}\\right) $$\r\n\r\n$$ x\\_{I\\_{2}} = y\\_{I\\_{2}} + m\\left(y\\_{I\\_{1}}\\right) $$","description_state":"present","introduced_year":null,"introduced_by":{"title":"NICE: Non-linear Independent Components Estimation","paper":"/paper/nice-non-linear-independent-components","first_author":"Laurent Dinh","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/nice-non-linear-independent-components"},"source":{"url":"http://arxiv.org/abs/1410.8516v6","title":"NICE: Non-linear Independent Components Estimation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/paultsw/nice_pytorch/blob/15cfc543fc3dc81ee70398b8dfc37b67269ede95/nice/models.py#L20","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Likelihood-Based Generative Models","url":"/methods/category/likelihood-based-generative-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":22,"archive_num_papers":22,"papers_newest_first":[{"paper":null,"title":"Towards Conversational AI for Disease Management","date":"2025-03-08","arxiv_id":"2503.06074","n_code_links":0,"syntology":null},{"paper":null,"title":"I See, Therefore I Do: Estimating Causal Effects for Image Treatments","date":"2024-11-28","arxiv_id":"2412.06810","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Learning Methods for the Noniterative Conditional Expectation G-Formula for Causal Inference from Complex Observational Data","date":"2024-10-28","arxiv_id":"2410.21531","n_code_links":0,"syntology":null},{"paper":null,"title":"The Solution for the CVPR2024 NICE Image Captioning Challenge","date":"2024-04-19","arxiv_id":"2404.12739","n_code_links":0,"syntology":null},{"paper":"/paper/nice-neurogenesis-inspired-contextual","title":"NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/nice-improving-panoptic-narrative-detection","title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","date":"2023-10-17","arxiv_id":"2310.10975","n_code_links":1,"syntology":null},{"paper":"/paper/towards-feasible-counterfactual-explanations","title":"Towards Feasible Counterfactual Explanations: A Taxonomy Guided Template-based NLG Method","date":"2023-10-03","arxiv_id":"2310.02019","n_code_links":1,"syntology":null},{"paper":"/paper/nice-noise-modulated-consistency","title":"NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"NICE: CVPR 2023 Challenge on Zero-shot Image Captioning","date":"2023-09-05","arxiv_id":"2309.01961","n_code_links":0,"syntology":null},{"paper":"/paper/non-iterative-coarse-to-fine-transformer","title":"Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration","date":"2023-07-07","arxiv_id":"2307.03421","n_code_links":1,"syntology":null},{"paper":null,"title":"Introduction to Non-Invasive Current Estimation (NICE)","date":"2023-01-17","arxiv_id":"2301.10237","n_code_links":0,"syntology":null},{"paper":null,"title":"Protein Co-Enrichment Analysis of Extracellular Vesicles","date":"2023-01-10","arxiv_id":"2301.04051","n_code_links":0,"syntology":null},{"paper":null,"title":"Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation","date":"2022-10-12","arxiv_id":"2210.06164","n_code_links":0,"syntology":null},{"paper":null,"title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","date":"2022-07-27","arxiv_id":"2207.13316","n_code_links":0,"syntology":null},{"paper":"/paper/the-devil-is-in-the-labels-noisy-label-1","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","date":"2022-06-07","arxiv_id":"2206.03014","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":null,"title":"Deep Learning based Prediction of MSI using MMR Markers in Colorectal Cancer","date":"2022-02-24","arxiv_id":"2203.00449","n_code_links":0,"syntology":null},{"paper":"/paper/nice-robust-scheduling-through-reinforcement","title":"NICE: Robust Scheduling through Reinforcement Learning-Guided Integer Programming","date":"2021-09-24","arxiv_id":"2109.12171","n_code_links":1,"syntology":null},{"paper":null,"title":"Approximation capabilities of measure-preserving neural networks","date":"2021-06-21","arxiv_id":"2106.10911","n_code_links":0,"syntology":null},{"paper":"/paper/nice-an-algorithm-for-nearest-instance","title":"NICE: An Algorithm for Nearest Instance Counterfactual Explanations","date":"2021-04-15","arxiv_id":"2104.07411","n_code_links":3,"syntology":null},{"paper":null,"title":"Generative Time-series Modeling with Fourier Flows","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/invariant-representation-learning-for","title":"Invariant Representation Learning for Treatment Effect Estimation","date":"2020-11-24","arxiv_id":"2011.12379","n_code_links":1,"syntology":{"ran":2,"of":3,"unverified":1,"pointer_only":3}},{"paper":"/paper/nice-non-linear-independent-components","title":"NICE: Non-linear Independent Components Estimation","date":"2014-10-30","arxiv_id":"1410.8516","n_code_links":19,"syntology":{"ran":24,"of":27,"unverified":3,"pointer_only":0}}],"papers_shown":22,"tasks":[{"task":"/task/causal-inference","name":"Causal Inference","papers":2},{"task":"/task/graph-generation","name":"Graph Generation","papers":2},{"task":"/task/image-captioning","name":"Image Captioning","papers":2},{"task":"/task/scene-graph-generation","name":"Scene Graph Generation","papers":2},{"task":null,"name":"counterfactual","papers":2},{"task":"/task/all","name":"All","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/causal-identification","name":"Causal Identification","papers":1},{"task":"/task/class-incremental-learning","name":"Class Incremental Learning","papers":1},{"task":"/task/clinical-knowledge","name":"Clinical Knowledge","papers":1},{"task":"/task/continual-learning","name":"Continual Learning","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/entity-disambiguation","name":"Entity Disambiguation","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":null,"name":"Hippocampus","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/image-registration","name":"Image Registration","papers":1},{"task":"/task/incremental-learning","name":"Incremental Learning","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1}],"tasks_shown":20,"n_tasks":39,"usage_by_year":[{"year":"2014","papers":1},{"year":"2020","papers":1},{"year":"2021","papers":4},{"year":"2022","papers":4},{"year":"2023","papers":7},{"year":"2024","papers":4},{"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/nice"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}