{"id":13712423,"url":"https://github.com/bcmi/Awesome-Few-Shot-Image-Generation","last_synced_at":"2025-05-06T22:31:11.763Z","repository":{"id":41123678,"uuid":"268741626","full_name":"bcmi/Awesome-Few-Shot-Image-Generation","owner":"bcmi","description":"A curated list of papers, code and resources pertaining to few-shot image generation.","archived":false,"fork":false,"pushed_at":"2023-06-03T12:51:02.000Z","size":84,"stargazers_count":374,"open_issues_count":1,"forks_count":46,"subscribers_count":26,"default_branch":"master","last_synced_at":"2025-04-30T15:09:18.416Z","etag":null,"topics":["data-augmentation","few-shot-generation","few-shot-image-generation","few-shot-learning"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bcmi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-06-02T08:16:37.000Z","updated_at":"2025-04-22T14:31:52.000Z","dependencies_parsed_at":"2024-05-28T09:54:10.127Z","dependency_job_id":"8222720f-60e2-45f7-83ef-9302b2eb1e81","html_url":"https://github.com/bcmi/Awesome-Few-Shot-Image-Generation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Few-Shot-Image-Generation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Few-Shot-Image-Generation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Few-Shot-Image-Generation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Few-Shot-Image-Generation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bcmi","download_url":"https://codeload.github.com/bcmi/Awesome-Few-Shot-Image-Generation/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252778991,"owners_count":21802862,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-augmentation","few-shot-generation","few-shot-image-generation","few-shot-learning"],"created_at":"2024-08-02T23:01:18.334Z","updated_at":"2025-05-06T22:31:11.488Z","avatar_url":"https://github.com/bcmi.png","language":null,"funding_links":[],"categories":["Table of Contents","Other Lists"],"sub_categories":["TeX Lists"],"readme":"# Awesome Few-Shot Image Generation  [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\n\nA curated list of resources including papers, datasets, and relevant links pertaining to few-shot image generation. Since few-shot image generation is a very broad concept, there are various experimental settings and research lines in the realm of few-shot image generation. \n\n\n## From Base Categories to Novel Categories\nThe generative model is trained on base categories and applied to novel categories with (optimization-based) or without finetuning (fusion-based and transformation-based). \n\n**Optimization-based methods:**\n+ Louis Clouâtre, Marc Demers: \"*FIGR: Few-shot Image Generation with Reptile.*\" CoRR abs/1901.02199 (2019) [[pdf]](https://arxiv.org/pdf/1901.02199.pdf) [[code]](https://arxiv.org/pdf/1901.02199.pdf)\n+ Weixin Liang, Zixuan Liu, Can Liu: \"*DAWSON: A Domain Adaptive Few Shot Generation Framework.*\" CoRR abs/2001.00576 (2020) [[pdf]](https://arxiv.org/pdf/2001.00576.pdf) [[code]](https://github.com/LC1905/musegan/)\n\n**Fusion-based methods:**\n+ Sergey Bartunov, Dmitry P. Vetrov: \"*Few-shot Generative Modelling with Generative Matching Networks.*\" AISTATS (2018) [[pdf]](http://proceedings.mlr.press/v84/bartunov18a/bartunov18a.pdf) [[code]](https://github.com/sbos/gmn)\n+ Davis Wertheimer, Omid Poursaeed, Bharath Hariharan: \"*Augmentation-interpolative Autoencoders for Unsupervised Few-shot Image Generation.*\" arXiv (2020). [[pdf]](https://arxiv.org/pdf/2011.13026.pdf)\n+ Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang: \"*MatchingGAN: Matching-based Few-shot Image Generation.*\" ICME (2020) [[pdf]](https://arxiv.org/pdf/2003.03497.pdf) [[code]](https://github.com/bcmi/MatchingGAN-Few-Shot-Image-Generation)\n+ Yan Hong, Li Niu, Jianfu Zhang, Weijie Zhao, Chen Fu, Liqing Zhang: \"*F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation.*\" ACM MM (2020) [[pdf]](https://arxiv.org/pdf/2008.01999.pdf) [[code]](https://github.com/bcmi/F2GAN-Few-Shot-Image-Generation)\n+ Zheng Gu, Wenbin Li, Jing Huo, Lei Wang, Yang Gao: \"*Lofgan: Fusing local representations for fewshot image generation.*\" ICCV (2021) [[pdf]](https://openaccess.thecvf.com/content/ICCV2021/papers/Gu_LoFGAN_Fusing_Local_Representations_for_Few-Shot_Image_Generation_ICCV_2021_paper.pdf) [[code]](https://github.com/edward3862/LoFGAN-pytorch)\n\n**Transformation-based methods:**\n+ Antreas Antoniou, Amos J. Storkey, Harrison Edwards: \"*Data Augmentation Generative Adversarial Networks.*\" stat (2018) [[pdf]](https://arxiv.org/pdf/1711.04340.pdf) [[code]](https://github.com/AntreasAntoniou/DAGAN) \n+  Guanqi Ding, Xinzhe Han, Shuhui Wang, Shuzhe Wu, Xin Jin, Dandan Tu, Qingming Huang: \"*Attribute Group Editing for Reliable Few-shot Image Generation.*\" CVPR (2022) [[pdf]](https://arxiv.org/pdf/2203.08422.pdf) [[code]](https://github.com/UniBester/AGE)\n+ Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang: \"*Few-shot Image Generation Using Discrete Content Representation.*\" ACM MM (2022) [[pdf]](https://arxiv.org/pdf/2207.10833.pdf)\n+ Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang: \"*DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta.*\" ECCV (2022) [[pdf]](https://arxiv.org/pdf/2009.08753.pdf) [[code]](https://github.com/bcmi/DeltaGAN-Few-Shot-Image-Generation)\n\n**Datasets:**\n+ Omniglot:  1623 handwritten characters from 50 different alphabets. Each of the 1623 characters was drawn online via Amazon's Mechanical Turk by 20 different people [[link]](https://github.com/brendenlake/omniglot/)\n+ EMNIST:  47 balanced classes [[link]](https://www.nist.gov/itl/products-and-services/emnist-dataset)\n+ FIGR: 17,375 classes of 1,548,256 images representing pictograms, ideograms, icons, emoticons or object or conception depictions [[link]](https://github.com/marcdemers/FIGR-8)\n+ VGG-Faces:  2395 categories [[link]](https://drive.google.com/drive/folders/15x2C11OrNeKLMzBDHrv8NPOwyre6H3O5)\n+ Flowers:  8189 images from 102 flower classes [[link]](https://www.robots.ox.ac.uk/~vgg/data/flowers/102/)\n+ Animal Faces: 117574 images from 149 animal classes [[link]](https://github.com/NVlabs/FUNIT)\n\n## From Large Dataset to Small Dataset\n\nThe generative model is trained on a large dataset (base domain/category) and transferred to a small dataset (novel domain/category). \n\n**Finetuning-based methods:** Only finetune a part of the model parameters *or* train a few additional parameters.\n+ Atsuhiro Noguchi, Tatsuya Harada: \"*Image generation from small datasets via batch statistics adaptation.*\" ICCV (2019) [[pdf]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Noguchi_Image_Generation_From_Small_Datasets_via_Batch_Statistics_Adaptation_ICCV_2019_paper.pdf) [[code]](http://github.com/nogu-atsu/small-dataset-image-generation)\n+ Esther Robb, Wen-Sheng Chu, Abhishek Kumar, Jia-Bin Huang: \"*Few-Shot Adaptation of Generative Adversarial Networks.*\" arXiv (2020) [[pdf]](https://arxiv.org/pdf/2010.11943.pdf) [[code]](https://github.com/e-271/few-shot-gan)\n+ Miaoyun Zhao, Yulai Cong, Lawrence Carin: \"*On Leveraging Pretrained GANs for Generation with Limited Data.*\" ICML (2020) [[pdf]](http://proceedings.mlr.press/v119/zhao20a/zhao20a.pdf) [[code]](https://github.com/MiaoyunZhao/GANTransferLimitedData)\n+ Yaxing Wang, Abel Gonzalez-Garcia, David Berga, Luis Herranz, Fahad Shahbaz Khan, Joost van de Weijer: \"*MineGAN: effective knowledge transfer from GANs to target domains with few images.*\" CVPR (2020) [[pdf]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_MineGAN_Effective_Knowledge_Transfer_From_GANs_to_Target_Domains_With_CVPR_2020_paper.pdf) [[code]](https://github.com/yaxingwang/MineGAN)\n+ Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-Man Cheung: \"*Few-shot Image Generation via Adaptation-Aware Kernel Modulation.*\" NeurIPS (2022) [[pdf]](https://arxiv.org/pdf/2210.16559.pdf) [[code]](https://github.com/yunqing-me/AdAM)\n+ Yunqing Zhao, Chao Du, Milad Abdollahzadeh, Tianyu Pang, Min Lin, Shuicheng Yan, Ngai-Man Cheung: \"*Exploring Incompatible Knowledge Transfer in Few-shot Image Generation.*\" CVPR (2023) [[pdf]](https://arxiv.org/pdf/2304.07574.pdf) [[code]](https://github.com/yunqing-me/RICK)\n+ Yuxuan Duan, Li Niu, Yan Hong, Liqing Zhang: \"*WeditGAN: Few-shot Image Generation via Latent Space Relocation.*\" arXiv (2023) [[pdf]](https://arxiv.org/pdf/2305.06671.pdf)\n\n**Regularization-based methods:** Regularize the transfer process based on the prior regularization knowledge, usually by imposing penalty on parameter/feature changes.\n+  Yijun Li, Richard Zhang, Jingwan Lu, Eli Shechtman: \"*Few-shot Image Generation with Elastic Weight Consolidation.*\" NeurIPS (2020) [[pdf]](https://arxiv.org/pdf/2012.02780.pdf) \n+ Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A. Efros, Yong Jae Lee, Eli Shechtman, Richard Zhang: \"*Few-shot Image Generation via Cross-domain Correspondence.*\" CVPR (2021) [[pdf]](https://arxiv.org/pdf/2104.06820.pdf) [[code]](https://github.com/utkarshojha/few-shot-gan-adaptation)\n+ Jiayu Xiao, Liang Li, Chaofei Wang, Zheng-Jun Zha, Qingming Huang: \"*Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment.*\" CVPR (2022) [[pdf]](https://arxiv.org/pdf/2203.04121.pdf) [[code]](https://github.com/StevenShaw1999/RSSA)\n+ Yunqing Zhao, Henghui Ding, Houjing Huang, Ngai-Man Cheung: \"*A Closer Look at Few-shot Image Generation.*\" CVPR (2022) [[pdf]](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhao_A_Closer_Look_at_Few-Shot_Image_Generation_CVPR_2022_paper.pdf) \n+ Xingzhong Hou, Boxiao Liu, Shuai Zhang, Lulin Shi, Zite Jiang, Haihang You: \"*Dynamic Weighted Semantic Correspondence for Few-Shot Image Generative Adaptation.*\" ACM MM (2022) [[pdf]](https://dl.acm.org/doi/pdf/10.1145/3503161.3548270)\n+ JingYuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan: \"*Few-shot Image Generation via Masked Discrimination.*\" arXiv (2022) [[pdf]](https://arxiv.org/pdf/2210.15194.pdf) \n\n**Datasets:** Sometimes a subset of a dataset is used as the target dataset.\n+ ImageNet: Over 1.4M images of 1k categories. [[link]](https://www.image-net.org/index.php)\n+ FFHQ (Flickr Faces HQ Dataset): 70k 1024\\*1024 face images proposed by NVIDIA in StyleGAN papers. [[link]](https://github.com/NVlabs/ffhq-dataset)\n+ Danbooru: Anime image dataset series. The latest version (2021) contains 4.9M images annotated with 162M tags. [[link]](https://www.gwern.net/Danbooru2021)\n+ AFHQ (Animal Faces HQ Dataset): 15k 512\\*512 animal images of three categories cat, dog and wildlife. [[link]](https://github.com/clovaai/stargan-v2/blob/master/README.md#animal-faces-hq-dataset-afhq)\n+ Artistic-Faces Dataset: 160 artistic portraits of 16 artists. [[link]](https://faculty.idc.ac.il/arik/site/foa/artistic-faces-dataset.asp)\n+ LSUN: 1M images for each of 10 scene categories and 20 object categories. [[link]](https://www.yf.io/p/lsun)\n+ CelebA: 203k face images of 10k identities. [[link]](https://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)\n\n## Only Small Dataset\n\nThe generative model is directly trained on a small dataset. \n\n+ Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, Song Han: \"*Differentiable Augmentation for Data-Efficient GAN Training.*\" NeurIPS (2020). [[pdf]](https://arxiv.org/pdf/2006.10738.pdf) [[code]](https://github.com/mit-han-lab/data-efficient-gans)\n+ Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal: \"*Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis.*\" ICLR (2021).               [[pdf]](https://arxiv.org/pdf/2101.04775v1.pdf) [[code]](https://github.com/odegeasslbc/FastGAN-pytorch)\n+ Mengyu Dai, Haibin Hang, Xiaoyang Guo: \"*Adaptive Feature Interpolation for Low-Shot Image Generation.*\" ECCV (2022). [[pdf]](https://arxiv.org/pdf/2112.02450.pdf)\n\nIn the extreme case, the generative model is directly trained on a single image. However, the learnt model generally only manipulates the repeated patterns in this image. \n\n+ Tamar Rott Shaham, Tali Dekel, Tomer Michaeli: \"*SinGAN: Learning a Generative Model from a Single Natural Image.*\" ICCV (2019). [[pdf]](https://openaccess.thecvf.com/content_ICCV_2019/papers/Shaham_SinGAN_Learning_a_Generative_Model_From_a_Single_Natural_Image_ICCV_2019_paper.pdf) [[code]](https://github.com/tamarott/SinGAN)\n+ Vadim Sushko, Jurgen Gall, Anna Khoreva: \"*One-Shot GAN: Learning to Generate Samples from Single Images and Videos.*\" CVPR workshop (2021). [[pdf]](https://openaccess.thecvf.com/content/CVPR2021W/LLID/papers/Sushko_One-Shot_GAN_Learning_To_Generate_Samples_From_Single_Images_and_CVPRW_2021_paper.pdf)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbcmi%2FAwesome-Few-Shot-Image-Generation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbcmi%2FAwesome-Few-Shot-Image-Generation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbcmi%2FAwesome-Few-Shot-Image-Generation/lists"}