{"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/exploiting-the-potential-of-standard","title":"Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search","arxiv_id":"1803.00370","date":"2018-03-01","proceeding":"ICML 2018 7","authors":["Masanori Suganuma","Mete Ozay","Takayuki Okatani"],"abstract":"Researchers have applied deep neural networks to image restoration tasks, in\nwhich they proposed various network architectures, loss functions, and training\nmethods. In particular, adversarial training, which is employed in recent\nstudies, seems to be a key ingredient to success. In this paper, we show that\nsimple convolutional autoencoders (CAEs) built upon only standard network\ncomponents, i.e., convolutional layers and skip connections, can outperform the\nstate-of-the-art methods which employ adversarial training and sophisticated\nloss functions. The secret is to employ an evolutionary algorithm to\nautomatically search for good architectures. Training optimized CAEs by\nminimizing the $\\ell_2$ loss between reconstructed images and their ground\ntruths using the ADAM optimizer is all we need. Our experimental results show\nthat this approach achieves 27.8 dB peak signal to noise ratio (PSNR) on the\nCelebA dataset and 40.4 dB on the SVHN dataset, compared to 22.8 dB and 33.0 dB\nprovided by the former state-of-the-art methods, respectively.","url_abs":"http://arxiv.org/abs/1803.00370v1","url_pdf":"http://arxiv.org/pdf/1803.00370v1.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":"exploiting-the-potential-of-standard","repo_url":"https://github.com/sg-nm/Evolutionary-Autoencoders","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.00370","atlas_url":"https://app.syntology.ai/?focus=1803.00370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.00370"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/sg-nm/Evolutionary-Autoencoders","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"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":"a376f4f1d756e187","entry":"arg_wrapper_mp","repo":"sg-nm/Evolutionary-Autoencoders","repo_kind":"official","path":"Denoising/cgp_config.py","file_url":"https://github.com/sg-nm/Evolutionary-Autoencoders/blob/HEAD/Denoising/cgp_config.py","link_basis":"first_harvest_node","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":"a376f4f1d756e187"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}