{"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/a-powerful-generative-model-using-random","title":"A Powerful Generative Model Using Random Weights for the Deep Image Representation","arxiv_id":"1606.04801","date":"2016-06-15","proceeding":"NeurIPS 2016 12","authors":["Kun He","Yan Wang","John Hopcroft"],"abstract":"To what extent is the success of deep visualization due to the training?\nCould we do deep visualization using untrained, random weight networks? To\naddress this issue, we explore new and powerful generative models for three\npopular deep visualization tasks using untrained, random weight convolutional\nneural networks. First we invert representations in feature spaces and\nreconstruct images from white noise inputs. The reconstruction quality is\nstatistically higher than that of the same method applied on well trained\nnetworks with the same architecture. Next we synthesize textures using scaled\ncorrelations of representations in multiple layers and our results are almost\nindistinguishable with the original natural texture and the synthesized\ntextures based on the trained network. Third, by recasting the content of an\nimage in the style of various artworks, we create artistic images with high\nperceptual quality, highly competitive to the prior work of Gatys et al. on\npretrained networks. To our knowledge this is the first demonstration of image\nrepresentations using untrained deep neural networks. Our work provides a new\nand fascinating tool to study the representation of deep network architecture\nand sheds light on new understandings on deep visualization.","url_abs":"http://arxiv.org/abs/1606.04801v2","url_pdf":"http://arxiv.org/pdf/1606.04801v2.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-powerful-generative-model-using-random","repo_url":"https://github.com/inzouzouwetrust/IMA_RWCNN_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.04801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04801"}},"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/inzouzouwetrust/IMA_RWCNN_project","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"dd9549af259ab897","entry":"random_phase_noise","repo":"inzouzouwetrust/IMA_RWCNN_project","repo_kind":"listed","path":"random_phase_noise.py","file_url":"https://github.com/inzouzouwetrust/IMA_RWCNN_project/blob/HEAD/random_phase_noise.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":"dd9549af259ab897"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}