{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/non-adversarial-image-synthesis-with","title":"Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors","arxiv_id":"1812.08985","date":"2018-12-21","proceeding":"CVPR 2019 6","authors":["Yedid Hoshen","Jitendra Malik"],"abstract":"Unconditional image generation has recently been dominated by generative\nadversarial networks (GANs). GAN methods train a generator which regresses\nimages from random noise vectors, as well as a discriminator that attempts to\ndifferentiate between the generated images and a training set of real images.\nGANs have shown amazing results at generating realistic looking images. Despite\ntheir success, GANs suffer from critical drawbacks including: unstable training\nand mode-dropping. The weaknesses in GANs have motivated research into\nalternatives including: variational auto-encoders (VAEs), latent embedding\nlearning methods (e.g. GLO) and nearest-neighbor based implicit maximum\nlikelihood estimation (IMLE). Unfortunately at the moment, GANs still\nsignificantly outperform the alternative methods for image generation. In this\nwork, we present a novel method - Generative Latent Nearest Neighbors (GLANN) -\nfor training generative models without adversarial training. GLANN combines the\nstrengths of IMLE and GLO in a way that overcomes the main drawbacks of each\nmethod. Consequently, GLANN generates images that are far better than GLO and\nIMLE. Our method does not suffer from mode collapse which plagues GAN training\nand is much more stable. Qualitative results show that GLANN outperforms a\nbaseline consisting of 800 GANs and VAEs on commonly used datasets. Our models\nare also shown to be effective for training truly non-adversarial unsupervised\nimage translation.","url_abs":"http://arxiv.org/abs/1812.08985v1","url_pdf":"http://arxiv.org/pdf/1812.08985v1.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":"non-adversarial-image-synthesis-with","repo_url":"https://github.com/yedidh/glann","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1812.08985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.08985"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yedidh/glann","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e26fd7f7907c2fc4","entry":"calculate_activation_statistics","repo":"yedidh/glann","repo_kind":"listed","path":"fid_score.py","file_url":"https://github.com/yedidh/glann/blob/HEAD/fid_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e26fd7f7907c2fc4"}},{"code_sha256_prefix":"0def50a351111624","entry":"calculate_frechet_distance","repo":"yedidh/glann","repo_kind":"listed","path":"fid_score.py","file_url":"https://github.com/yedidh/glann/blob/HEAD/fid_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0def50a351111624"}},{"code_sha256_prefix":"29b09c5229b5a227","entry":"get_activations","repo":"yedidh/glann","repo_kind":"listed","path":"fid_score.py","file_url":"https://github.com/yedidh/glann/blob/HEAD/fid_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"29b09c5229b5a227"}},{"code_sha256_prefix":"9e9a6dc9e188fa21","entry":"sample_gaussian","repo":"yedidh/glann","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/yedidh/glann/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9e9a6dc9e188fa21"}},{"code_sha256_prefix":"e61224a5533342ef","entry":"unnorm","repo":"yedidh/glann","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/yedidh/glann/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e61224a5533342ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}