{"url":"/method/sig","slug":"sig","name":"SIG","full_name":"Sliced Iterative Generator","full_name_withheld":false,"description_markdown":"The **Sliced Iterative Generator (SIG)** is an iterative generative model that is a Normalizing Flow (NF), but shares the advantages of Generative Adversarial Networks (GANs). The model is based on iterative Optimal Transport of a series of 1D slices through the data space, matching on each slice the probability distribution function (PDF) of the samples to the data. To improve the efficiency, the directions of the orthogonal slices are chosen to maximize the PDF difference between the generated samples and the data using Wasserstein distance at each iteration. A patch based approach is adopted to model the images in a hierarchical way, enabling the model to scale well to high dimensions. \r\n\r\nUnlike GANs, SIG has a NF structure and allows efficient likelihood evaluations that can be used in downstream tasks. While SIG has a deep neural network architecture, the approach deviates significantly from the current deep learning paradigm, as it does not use concepts such as mini-batching, stochastic gradient descent, gradient back-propagation through deep layers, or non-convex loss function optimization. SIG is very insensitive to hyper-parameter tuning, making it a useful generator tool for ML experts and non-experts alike.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2007.00674v3","title":"Sliced Iterative Normalizing Flows","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/biweidai/SIG","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":17,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Quality Assessment of Noisy and Enhanced Speech with Limited Data: UWB-NTIS System for VoiceMOS 2024 and Beyond","date":"2025-05-31","arxiv_id":"2506.00506","n_code_links":0,"syntology":null},{"paper":null,"title":"Keras Sig: Efficient Path Signature Computation on GPU in Keras 3","date":"2025-01-14","arxiv_id":"2501.08455","n_code_links":0,"syntology":null},{"paper":null,"title":"SIG: A Synthetic Identity Generation Pipeline for Generating Evaluation Datasets for Face Recognition","date":"2024-09-12","arxiv_id":"2409.08345","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-safety-for-autonomous-agents-in","title":"Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding","date":"2024-07-05","arxiv_id":"2407.04343","n_code_links":1,"syntology":null},{"paper":null,"title":"Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework","date":"2024-02-10","arxiv_id":"2402.06875","n_code_links":0,"syntology":null},{"paper":"/paper/sig-speaker-identification-in-literature-via","title":"SIG: Speaker Identification in Literature via Prompt-Based Generation","date":"2023-12-22","arxiv_id":"2312.14590","n_code_links":1,"syntology":null},{"paper":null,"title":"A New Baseline Assumption of Integated Gradients Based on Shaply value","date":"2023-10-07","arxiv_id":"2310.04821","n_code_links":0,"syntology":null},{"paper":"/paper/subspace-identification-for-multi-source","title":"Subspace Identification for Multi-Source Domain Adaptation","date":"2023-10-07","arxiv_id":"2310.04723","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":null,"title":"Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data","date":"2023-09-27","arxiv_id":"2309.15635","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-integrated-gradients-a-simple-but","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","date":"2023-05-25","arxiv_id":"2305.15853","n_code_links":1,"syntology":null},{"paper":null,"title":"ICASSP 2023 Speech Signal Improvement Challenge","date":"2023-03-12","arxiv_id":"2303.06566","n_code_links":0,"syntology":null},{"paper":null,"title":"CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis","date":"2023-02-28","arxiv_id":"2302.14370","n_code_links":0,"syntology":null},{"paper":"/paper/petsgan-rethinking-priors-for-single-image","title":"PetsGAN: Rethinking Priors for Single Image Generation","date":"2022-03-03","arxiv_id":"2203.01488","n_code_links":2,"syntology":null},{"paper":"/paper/icassp-2022-deep-noise-suppression-challenge","title":"ICASSP 2022 Deep Noise Suppression Challenge","date":"2022-02-27","arxiv_id":"2202.13288","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}},{"paper":"/paper/aura-privacy-preserving-augmentation-to","title":"Aura: Privacy-preserving Augmentation to Improve Test Set Diversity in Speech Enhancement","date":"2021-10-08","arxiv_id":"2110.04391","n_code_links":1,"syntology":null},{"paper":"/paper/dnsmos-p-835-a-non-intrusive-perceptual","title":"DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors","date":"2021-10-05","arxiv_id":"2110.01763","n_code_links":1,"syntology":null},{"paper":"/paper/sliced-iterative-generator","title":"Sliced Iterative Normalizing Flows","date":"2020-07-01","arxiv_id":"2007.00674","n_code_links":2,"syntology":{"ran":1,"of":4,"unverified":3,"pointer_only":4}}],"papers_shown":17,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":4},{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":1},{"task":"/task/autonomous-navigation","name":"Autonomous Navigation","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/c-code","name":"C++ code","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/density-estimation","name":"Density Estimation","papers":1},{"task":"/task/disentanglement","name":"Disentanglement","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/dynamic-time-warping","name":"Dynamic Time Warping","papers":1},{"task":"/task/face-recognition","name":"Face Recognition","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-manipulation","name":"Image Manipulation","papers":1},{"task":"/task/one-shot-learning","name":"One-Shot Learning","papers":1},{"task":"/task/out-of-distribution-detection","name":"Out-of-Distribution Detection","papers":1},{"task":null,"name":"Position","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1}],"tasks_shown":20,"n_tasks":32,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2023","papers":7},{"year":"2024","papers":3},{"year":"2025","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sig"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}