{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-u-net-based-discriminator-for-generative","title":"A U-Net Based Discriminator for Generative Adversarial Networks","arxiv_id":"2002.12655","date":"2020-02-28","proceeding":null,"authors":["Edgar Schönfeld","Bernt Schiele","Anna Khoreva"],"abstract":"Among the major remaining challenges for generative adversarial networks (GANs) is the capacity to synthesize globally and locally coherent images with object shapes and textures indistinguishable from real images. To target this issue we propose an alternative U-Net based discriminator architecture, borrowing the insights from the segmentation literature. The proposed U-Net based architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images, by providing the global image feedback as well. Empowered by the per-pixel response of the discriminator, we further propose a per-pixel consistency regularization technique based on the CutMix data augmentation, encouraging the U-Net discriminator to focus more on semantic and structural changes between real and fake images. This improves the U-Net discriminator training, further enhancing the quality of generated samples. The novel discriminator improves over the state of the art in terms of the standard distribution and image quality metrics, enabling the generator to synthesize images with varying structure, appearance and levels of detail, maintaining global and local realism. Compared to the BigGAN baseline, we achieve an average improvement of 2.7 FID points across FFHQ, CelebA, and the newly introduced COCO-Animals dataset. The code is available at https://github.com/boschresearch/unetgan.","url_abs":"https://arxiv.org/abs/2002.12655v2","url_pdf":"https://arxiv.org/pdf/2002.12655v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-u-net-based-discriminator-for-generative","repo_url":"https://github.com/boschresearch/unetgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"a-u-net-based-discriminator-for-generative","repo_url":"https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-u-net-based-discriminator-for-generative","repo_url":"https://github.com/xingchenzhao/deep-learning-team-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"biggan","method_name":"BigGAN"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"conditional-batch-normalization","method_name":"Conditional Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cutmix","method_name":"CutMix"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"early-stopping","method_name":"Early Stopping"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"off-diagonal-orthogonal-regularization","method_name":"Off-Diagonal Orthogonal Regularization"},{"method_slug":"projection-discriminator","method_name":"Projection Discriminator"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sagan","method_name":"SAGAN"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"},{"method_slug":"ttur","method_name":"TTUR"},{"method_slug":"truncation-trick","method_name":"Truncation Trick"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-coco-animals","task":"Conditional Image Generation","dataset":"COCO-Animals","model":"U-Net GAN","rank_in_archive_order":1,"of":2,"metrics":{"FID":"13.73","IS":"12.29"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-coco-animals","task":"Conditional Image Generation","dataset":"COCO-Animals","model":"BigGAN","rank_in_archive_order":2,"of":2,"metrics":{"FID":"16.37","IS":"11.77"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-128x128","task":"Image Generation","dataset":"CelebA 128x128","model":"U-Net GAN","rank_in_archive_order":1,"of":5,"metrics":{"FID":"2.95","Inception score":"3.43"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-hq-128x128","task":"Image Generation","dataset":"CelebA-HQ 128x128","model":"U-Net GAN","rank_in_archive_order":1,"of":7,"metrics":{"FID":"2.03","Inception score":"3.33"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","task":"Image Generation","dataset":"FFHQ 256 x 256","model":"U-Net GAN","rank_in_archive_order":30,"of":51,"metrics":{"FID":"7.48"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","task":"Image Generation","dataset":"FFHQ 256 x 256","model":"BigGAN","rank_in_archive_order":36,"of":51,"metrics":{"FID":"11.48"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.12655","atlas_url":"https://app.syntology.ai/?focus=2002.12655","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2002.12655"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2002.12655\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2002.12655"},"call":"get_concepts_for_paper(arxiv_id=\"2002.12655\")"}],"by_repo":[{"repo":"boschresearch/unetgan","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xingchenzhao/deep-learning-team-project","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"be3871d148b15d54743f5e7aa30f8ded779eb464c40610ac217dbb9edf3e3ddb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}