{"url":"/method/oasis","slug":"oasis","name":"OASIS","full_name":"OASIS","full_name_withheld":false,"description_markdown":"OASIS is a [GAN](https://paperswithcode.com/method/gan)-based model to translate semantic label maps into realistic-looking images. The model builds on preceding work such as [Pix2Pix](https://paperswithcode.com/method/pix2pix) and SPADE. OASIS introduces the following innovations:  \r\n\r\n1. The method is not dependent on the perceptual loss, which is commonly used for the semantic image synthesis task. A [VGG](https://paperswithcode.com/method/vgg) network trained on ImageNet is routinely employed as the perceptual loss to strongly improve the synthesis quality. The authors show that this perceptual loss also has negative effects: First, it reduces the diversity of the generated images. Second, it negatively influences the color distribution to be more biased towards ImageNet. OASIS eliminates the dependence on the perceptual loss by changing the common discriminator design: The OASIS discriminator segments an image into one of the real classes or an additional fake class. In doing so, it makes more efficient use of the label maps that the discriminator normally receives. This distinguishes the discriminator from the commonly used encoder-shaped discriminators, which concatenate the label maps to the input image and predict a single score per image. With the more fine-grained supervision through the loss of the OASIS discriminator, the perceptual loss is shown to become unnecessary.\r\n\r\n2. A user can generate a diverse set of images per label map by simply resampling noise. This is achieved by conditioning the [spatially-adaptive denormalization](https://arxiv.org/abs/1903.07291) module in each layer of the GAN generator directly on spatially replicated input noise. A side effect of this conditioning is that at inference time an image can be resampled either globally or locally (either the complete image changes or a restricted region in the image).","description_state":"present","introduced_year":null,"introduced_by":{"title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","paper":"/paper/you-only-need-adversarial-supervision-for-1","first_author":"Vadim Sushko","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/you-only-need-adversarial-supervision-for-1"},"source":{"url":"https://arxiv.org/abs/2012.04781v3","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/boschresearch/OASIS","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Conditional Image-to-Image Translation Models","url":"/methods/category/conditional-image-to-image-translation-models","pwc_aliases":[]}],"n_papers_tagged":50,"archive_num_papers":50,"papers_newest_first":[{"paper":"/paper/matrix-game-interactive-world-foundation","title":"Matrix-Game: Interactive World Foundation Model","date":"2025-06-23","arxiv_id":"2506.18701","n_code_links":1,"syntology":null},{"paper":null,"title":"OASIS: Online Sample Selection for Continual Visual Instruction Tuning","date":"2025-05-27","arxiv_id":"2506.02011","n_code_links":0,"syntology":null},{"paper":null,"title":"Reconsider the Template Mesh in Deep Learning-based Mesh Reconstruction","date":"2025-05-21","arxiv_id":"2505.15285","n_code_links":0,"syntology":null},{"paper":null,"title":"FF-PNet: A Pyramid Network Based on Feature and Field for Brain Image Registration","date":"2025-05-08","arxiv_id":"2505.04938","n_code_links":0,"syntology":null},{"paper":null,"title":"SAM-Guided Robust Representation Learning for One-Shot 3D Medical Image Segmentation","date":"2025-04-29","arxiv_id":"2504.20501","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Robustness of Cortical Morphometry in the presence of white matter lesions, using Diffusion Models for Lesion Filling","date":"2025-03-26","arxiv_id":"2503.20571","n_code_links":0,"syntology":null},{"paper":"/paper/oasis-one-image-is-all-you-need-for","title":"Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis","date":"2025-03-11","arxiv_id":"2503.08741","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":"/paper/oasis-order-augmented-strategy-for-improved","title":"OASIS: Order-Augmented Strategy for Improved Code Search","date":"2025-03-11","arxiv_id":"2503.08161","n_code_links":0,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":null,"title":"Adaptive parameters identification for nonlinear dynamics using deep permutation invariant networks","date":"2025-01-20","arxiv_id":"2501.11350","n_code_links":0,"syntology":null},{"paper":null,"title":"OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes","date":"2025-01-01","arxiv_id":"2501.00962","n_code_links":0,"syntology":null},{"paper":null,"title":"How reproducible are data-driven subtypes of Alzheimer's disease atrophy?","date":"2024-11-29","arxiv_id":"2412.00160","n_code_links":0,"syntology":null},{"paper":"/paper/oasis-open-agents-social-interaction","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","date":"2024-11-18","arxiv_id":"2411.11581","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Online Test of a Neural Network Deep Convection Parameterization in ARP-GEM1","date":"2024-10-29","arxiv_id":"2410.21920","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":"H-SGANet: Hybrid Sparse Graph Attention Network for Deformable Medical Image Registration","date":"2024-08-29","arxiv_id":"2408.16719","n_code_links":0,"syntology":null},{"paper":"/paper/oasis-conditional-distribution-shaping-for","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","date":"2024-07-19","arxiv_id":"2407.14653","n_code_links":1,"syntology":{"ran":4,"of":8,"unverified":4,"pointer_only":0}},{"paper":null,"title":"Introducing VaDA: Novel Image Segmentation Model for Maritime Object Segmentation Using New Dataset","date":"2024-07-12","arxiv_id":"2407.09005","n_code_links":0,"syntology":null},{"paper":null,"title":"Local Methods with Adaptivity via Scaling","date":"2024-06-02","arxiv_id":"2406.00846","n_code_links":0,"syntology":null},{"paper":null,"title":"A Machine Learning Approach for Identifying Anatomical Biomarkers of Early Mild Cognitive Impairment","date":"2024-05-29","arxiv_id":"2407.00040","n_code_links":0,"syntology":null},{"paper":"/paper/a-light-weight-rectangular-decomposition","title":"A light-weight rectangular decomposition large kernel convolution network for deformable medical image registration.","date":"2024-05-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Computer aided diagnosis system for Alzheimers disease using principal component analysis and machine learning based approaches","date":"2024-04-15","arxiv_id":"2405.09553","n_code_links":0,"syntology":null},{"paper":"/paper/efficientmorph-parameter-efficient","title":"EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration","date":"2024-03-16","arxiv_id":"2403.11026","n_code_links":1,"syntology":null},{"paper":"/paper/hyperpredict-estimating-hyperparameter","title":"HyperPredict: Estimating Hyperparameter Effects for Instance-Specific Regularization in Deformable Image Registration","date":"2024-03-04","arxiv_id":"2403.02069","n_code_links":1,"syntology":null},{"paper":null,"title":"3D Volumetric Super-Resolution in Radiology Using 3D RRDB-GAN","date":"2024-02-06","arxiv_id":"2402.04171","n_code_links":0,"syntology":null},{"paper":null,"title":"ADAPT: Alzheimer Diagnosis through Adaptive Profiling Transformers","date":"2024-01-12","arxiv_id":"2401.06349","n_code_links":0,"syntology":null},{"paper":null,"title":"OASIS: Offsetting Active Reconstruction Attacks in Federated Learning","date":"2023-11-23","arxiv_id":"2311.13739","n_code_links":0,"syntology":null},{"paper":"/paper/oasis-data-curation-and-assessment-system-for","title":"Oasis: Data Curation and Assessment System for Pretraining of Large Language Models","date":"2023-11-21","arxiv_id":"2311.12537","n_code_links":1,"syntology":null},{"paper":null,"title":"A Plug-and-Play Image Registration Network","date":"2023-10-06","arxiv_id":"2310.04297","n_code_links":0,"syntology":null},{"paper":null,"title":"Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software","date":"2023-08-18","arxiv_id":"2308.09810","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-registration","name":"Image Registration","papers":8},{"task":"/task/medical-image-registration","name":"Medical Image Registration","papers":6},{"task":"/task/image-generation","name":"Image Generation","papers":4},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":4},{"task":"/task/deep-learning","name":"Deep Learning","papers":3},{"task":"/task/deformable-medical-image-registration","name":"Deformable Medical Image Registration","papers":3},{"task":"/task/large-language-model","name":"Large Language Model","papers":3},{"task":"/task/representation-learning","name":"Representation Learning","papers":3},{"task":"/task/segmentation","name":"Segmentation","papers":3},{"task":"/task/attribute","name":"Attribute","papers":2},{"task":"/task/binary-classification","name":"Binary Classification","papers":2},{"task":"/task/federated-learning","name":"Federated Learning","papers":2},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/retrieval","name":"Retrieval","papers":2},{"task":"/task/active-learning","name":"Active Learning","papers":1},{"task":"/task/all","name":"All","papers":1},{"task":"/task/anatomy","name":"Anatomy","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1}],"tasks_shown":20,"n_tasks":77,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":9},{"year":"2022","papers":4},{"year":"2023","papers":11},{"year":"2024","papers":15},{"year":"2025","papers":10}],"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/oasis"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}