{"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/i-revnet-deep-invertible-networks","title":"i-RevNet: Deep Invertible Networks","arxiv_id":"1802.07088","date":"2018-02-20","proceeding":"ICLR 2018 1","authors":["Jörn-Henrik Jacobsen","Arnold Smeulders","Edouard Oyallon"],"abstract":"It is widely believed that the success of deep convolutional networks is\nbased on progressively discarding uninformative variability about the input\nwith respect to the problem at hand. This is supported empirically by the\ndifficulty of recovering images from their hidden representations, in most\ncommonly used network architectures. In this paper we show via a one-to-one\nmapping that this loss of information is not a necessary condition to learn\nrepresentations that generalize well on complicated problems, such as ImageNet.\nVia a cascade of homeomorphic layers, we build the i-RevNet, a network that can\nbe fully inverted up to the final projection onto the classes, i.e. no\ninformation is discarded. Building an invertible architecture is difficult, for\none, because the local inversion is ill-conditioned, we overcome this by\nproviding an explicit inverse. An analysis of i-RevNets learned representations\nsuggests an alternative explanation for the success of deep networks by a\nprogressive contraction and linear separation with depth. To shed light on the\nnature of the model learned by the i-RevNet we reconstruct linear\ninterpolations between natural image representations.","url_abs":"http://arxiv.org/abs/1802.07088v1","url_pdf":"http://arxiv.org/pdf/1802.07088v1.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":"i-revnet-deep-invertible-networks","repo_url":"https://github.com/jhjacobsen/pytorch-i-revnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"i-revnet-deep-invertible-networks","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.07088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07088"}},"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/jhjacobsen/pytorch-i-revnet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"bb104479d26e39c3","entry":"get_hms","repo":"jhjacobsen/pytorch-i-revnet","repo_kind":"official","path":"models/utils_cifar.py","file_url":"https://github.com/jhjacobsen/pytorch-i-revnet/blob/HEAD/models/utils_cifar.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb104479d26e39c3"}},{"code_sha256_prefix":"2d15f050207aff53","entry":"merge","repo":"jhjacobsen/pytorch-i-revnet","repo_kind":"official","path":"models/model_utils.py","file_url":"https://github.com/jhjacobsen/pytorch-i-revnet/blob/HEAD/models/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d15f050207aff53"}},{"code_sha256_prefix":"781553d9de1bec97","entry":"split","repo":"jhjacobsen/pytorch-i-revnet","repo_kind":"official","path":"models/model_utils.py","file_url":"https://github.com/jhjacobsen/pytorch-i-revnet/blob/HEAD/models/model_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"781553d9de1bec97"}},{"code_sha256_prefix":"947a620765d795b2","entry":"learning_rate","repo":"jhjacobsen/pytorch-i-revnet","repo_kind":"official","path":"models/utils_cifar.py","file_url":"https://github.com/jhjacobsen/pytorch-i-revnet/blob/HEAD/models/utils_cifar.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":"947a620765d795b2"}},{"code_sha256_prefix":"dab1f482d324fc51","entry":"test","repo":"jhjacobsen/pytorch-i-revnet","repo_kind":"official","path":"models/utils_cifar.py","file_url":"https://github.com/jhjacobsen/pytorch-i-revnet/blob/HEAD/models/utils_cifar.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":"dab1f482d324fc51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}