{"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/plug-play-generative-networks-conditional","title":"Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space","arxiv_id":"1612.00005","date":"2016-11-30","proceeding":"CVPR 2017 7","authors":["Anh Nguyen","Jeff Clune","Yoshua Bengio","Alexey Dosovitskiy","Jason Yosinski"],"abstract":"Generating high-resolution, photo-realistic images has been a long-standing\ngoal in machine learning. Recently, Nguyen et al. (2016) showed one interesting\nway to synthesize novel images by performing gradient ascent in the latent\nspace of a generator network to maximize the activations of one or multiple\nneurons in a separate classifier network. In this paper we extend this method\nby introducing an additional prior on the latent code, improving both sample\nquality and sample diversity, leading to a state-of-the-art generative model\nthat produces high quality images at higher resolutions (227x227) than previous\ngenerative models, and does so for all 1000 ImageNet categories. In addition,\nwe provide a unified probabilistic interpretation of related activation\nmaximization methods and call the general class of models \"Plug and Play\nGenerative Networks\". PPGNs are composed of 1) a generator network G that is\ncapable of drawing a wide range of image types and 2) a replaceable \"condition\"\nnetwork C that tells the generator what to draw. We demonstrate the generation\nof images conditioned on a class (when C is an ImageNet or MIT Places\nclassification network) and also conditioned on a caption (when C is an image\ncaptioning network). Our method also improves the state of the art of\nMultifaceted Feature Visualization, which generates the set of synthetic inputs\nthat activate a neuron in order to better understand how deep neural networks\noperate. Finally, we show that our model performs reasonably well at the task\nof image inpainting. While image models are used in this paper, the approach is\nmodality-agnostic and can be applied to many types of data.","url_abs":"http://arxiv.org/abs/1612.00005v2","url_pdf":"http://arxiv.org/pdf/1612.00005v2.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":"plug-play-generative-networks-conditional","repo_url":"https://github.com/Evolving-AI-Lab/ppgn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.00005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00005"}},"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/Evolving-AI-Lab/ppgn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"64ee22db097899ff","entry":"deprocess","repo":"Evolving-AI-Lab/ppgn","repo_kind":"listed","path":"util.py","file_url":"https://github.com/Evolving-AI-Lab/ppgn/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64ee22db097899ff"}},{"code_sha256_prefix":"a4d31f2245435a58","entry":"get_image_size","repo":"Evolving-AI-Lab/ppgn","repo_kind":"listed","path":"util.py","file_url":"https://github.com/Evolving-AI-Lab/ppgn/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4d31f2245435a58"}},{"code_sha256_prefix":"74a74b343c22fd81","entry":"normalize","repo":"Evolving-AI-Lab/ppgn","repo_kind":"listed","path":"util.py","file_url":"https://github.com/Evolving-AI-Lab/ppgn/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74a74b343c22fd81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}