{"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/deep-feature-consistent-variational","title":"Deep Feature Consistent Variational Autoencoder","arxiv_id":"1610.00291","date":"2016-10-02","proceeding":null,"authors":["Xianxu Hou","Linlin Shen","Ke Sun","Guoping Qiu"],"abstract":"We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent deep learning works such as style transfer, we employ a pre-trained deep convolutional neural network (CNN) and use its hidden features to define a feature perceptual loss for VAE training. Evaluated on the CelebA face dataset, we show that our model produces better results than other methods in the literature. We also show that our method can produce latent vectors that can capture the semantic information of face expressions and can be used to achieve state-of-the-art performance in facial attribute prediction.","url_abs":"https://arxiv.org/abs/1610.00291v2","url_pdf":"https://arxiv.org/pdf/1610.00291v2.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":"deep-feature-consistent-variational","repo_url":"https://github.com/AntixK/PyTorch-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/Nanway/dfc-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/UdbhavPrasad072300/Generate-Fake-Faces-with-CVAE-in-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/bhpfelix/Variational-Autoencoder-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/bogedy/intro_dfc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/inkplatform/beta-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/ku2482/vae.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/lukeditria/cnn-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/matthew-liu/beta-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/nmichlo/disent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/peria1/VAEconvMNIST","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/svenrdz/DFC-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/vinoth654321/Beta-Vae-face-dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-feature-consistent-variational","repo_url":"https://github.com/Dylan-get/Deep-Feature-Consistent-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.00291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.00291"}},"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/AntixK/PyTorch-VAE","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Nanway/dfc-vae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/matthew-liu/beta-vae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/inkplatform/beta-vae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UdbhavPrasad072300/Generate-Fake-Faces-with-CVAE-in-PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ku2482/vae.pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Dylan-get/Deep-Feature-Consistent-VAE","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vinoth654321/Beta-Vae-face-dataset","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nmichlo/disent","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/svenrdz/DFC-VAE","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukeditria/cnn-vae","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/peria1/VAEconvMNIST","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bogedy/intro_dfc","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bhpfelix/Variational-Autoencoder-PyTorch","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"listed":{"samples":8,"ran":2,"repositories":5}},"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":5,"samples":[{"code_sha256_prefix":"310bb444965578fb","entry":"loss_function","repo":"peria1/VAEconvMNIST","repo_kind":"listed","path":"src/vanilla_vae.py","file_url":"https://github.com/peria1/VAEconvMNIST/blob/HEAD/src/vanilla_vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"310bb444965578fb"}},{"code_sha256_prefix":"151aee3ffaced99a","entry":"loss_function","repo":"bhpfelix/Variational-Autoencoder-PyTorch","repo_kind":"listed","path":"src/vanila_vae.py","file_url":"https://github.com/bhpfelix/Variational-Autoencoder-PyTorch/blob/HEAD/src/vanila_vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"151aee3ffaced99a"}},{"code_sha256_prefix":"b2870cfaccbe1020","entry":"get_df","repo":"ku2482/vae.pytorch","repo_kind":"listed","path":"utils/anno.py","file_url":"https://github.com/ku2482/vae.pytorch/blob/HEAD/utils/anno.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":"b2870cfaccbe1020"}},{"code_sha256_prefix":"6d449298eb9f6365","entry":"get_norm_layer","repo":"lukeditria/cnn-vae","repo_kind":"listed","path":"RES_VAE_Dynamic.py","file_url":"https://github.com/lukeditria/cnn-vae/blob/HEAD/RES_VAE_Dynamic.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":"6d449298eb9f6365"}},{"code_sha256_prefix":"6d3c813b7561493d","entry":"inception_score","repo":"Dylan-get/Deep-Feature-Consistent-VAE","repo_kind":"listed","path":"IS/is_torch.py","file_url":"https://github.com/Dylan-get/Deep-Feature-Consistent-VAE/blob/HEAD/IS/is_torch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6d3c813b7561493d"}},{"code_sha256_prefix":"537c6692279cb920","entry":"inception_score","repo":"Dylan-get/Deep-Feature-Consistent-VAE","repo_kind":"listed","path":"IS/is_paddle.py","file_url":"https://github.com/Dylan-get/Deep-Feature-Consistent-VAE/blob/HEAD/IS/is_paddle.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"537c6692279cb920"}},{"code_sha256_prefix":"f344dca39109fdf5","entry":"inception_score","repo":"Dylan-get/Deep-Feature-Consistent-VAE","repo_kind":"listed","path":"IS/is_source.py","file_url":"https://github.com/Dylan-get/Deep-Feature-Consistent-VAE/blob/HEAD/IS/is_source.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f344dca39109fdf5"}},{"code_sha256_prefix":"25aa7d6d0c4aeff8","entry":"parse_annotation","repo":"ku2482/vae.pytorch","repo_kind":"listed","path":"utils/anno.py","file_url":"https://github.com/ku2482/vae.pytorch/blob/HEAD/utils/anno.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":"25aa7d6d0c4aeff8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}