{"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/making-sense-of-cnns-interpreting-deep","title":"Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs","arxiv_id":"2008.01777","date":"2020-08-04","proceeding":"ECCV 2020 8","authors":["Robin Rombach","Patrick Esser","Björn Ommer"],"abstract":"To tackle increasingly complex tasks, it has become an essential ability of neural networks to learn abstract representations. These task-specific representations and, particularly, the invariances they capture turn neural networks into black box models that lack interpretability. To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to. We present an approach based on INNs that (i) recovers the task-specific, learned invariances by disentangling the remaining factor of variation in the data and that (ii) invertibly transforms these recovered invariances combined with the model representation into an equally expressive one with accessible semantic concepts. As a consequence, neural network representations become understandable by providing the means to (i) expose their semantic meaning, (ii) semantically modify a representation, and (iii) visualize individual learned semantic concepts and invariances. Our invertible approach significantly extends the abilities to understand black box models by enabling post-hoc interpretations of state-of-the-art networks without compromising their performance. Our implementation is available at https://compvis.github.io/invariances/ .","url_abs":"https://arxiv.org/abs/2008.01777v1","url_pdf":"https://arxiv.org/pdf/2008.01777v1.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":"making-sense-of-cnns-interpreting-deep","repo_url":"https://github.com/CompVis/invariances","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.01777","atlas_url":"https://app.syntology.ai/?focus=2008.01777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01777"}},"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/CompVis/invariances","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":3,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"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":"07d90bd6ae1be7db","entry":"md5_hash","repo":"CompVis/invariances","repo_kind":"listed","path":"invariances/util/ckpt_util.py","file_url":"https://github.com/CompVis/invariances/blob/HEAD/invariances/util/ckpt_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07d90bd6ae1be7db"}},{"code_sha256_prefix":"c2aeb4c49730718a","entry":"repeat_channels","repo":"CompVis/invariances","repo_kind":"listed","path":"invariances/iterator/base_trainer.py","file_url":"https://github.com/CompVis/invariances/blob/HEAD/invariances/iterator/base_trainer.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":"c2aeb4c49730718a"}},{"code_sha256_prefix":"3d7adb2f95674903","entry":"tonp","repo":"CompVis/invariances","repo_kind":"listed","path":"invariances/iterator/base_trainer.py","file_url":"https://github.com/CompVis/invariances/blob/HEAD/invariances/iterator/base_trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d7adb2f95674903"}},{"code_sha256_prefix":"5866cfd90792c154","entry":"totorch","repo":"CompVis/invariances","repo_kind":"listed","path":"invariances/iterator/base_trainer.py","file_url":"https://github.com/CompVis/invariances/blob/HEAD/invariances/iterator/base_trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5866cfd90792c154"}},{"code_sha256_prefix":"ee20e6e2564f076a","entry":"get_ckpt_path","repo":"CompVis/invariances","repo_kind":"listed","path":"invariances/util/ckpt_util.py","file_url":"https://github.com/CompVis/invariances/blob/HEAD/invariances/util/ckpt_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":"ee20e6e2564f076a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}