{"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/diverse-feature-visualizations-reveal","title":"Diverse feature visualizations reveal invariances in early layers of deep neural networks","arxiv_id":"1807.10589","date":"2018-07-27","proceeding":"ECCV 2018 9","authors":["Santiago A. Cadena","Marissa A. Weis","Leon A. Gatys","Matthias Bethge","Alexander S. Ecker"],"abstract":"Visualizing features in deep neural networks (DNNs) can help understanding\ntheir computations. Many previous studies aimed to visualize the selectivity of\nindividual units by finding meaningful images that maximize their activation.\nHowever, comparably little attention has been paid to visualizing to what image\ntransformations units in DNNs are invariant. Here we propose a method to\ndiscover invariances in the responses of hidden layer units of deep neural\nnetworks. Our approach is based on simultaneously searching for a batch of\nimages that strongly activate a unit while at the same time being as distinct\nfrom each other as possible. We find that even early convolutional layers in\nVGG-19 exhibit various forms of response invariance: near-perfect phase\ninvariance in some units and invariance to local diffeomorphic transformations\nin others. At the same time, we uncover representational differences with\nResNet-50 in its corresponding layers. We conclude that invariance\ntransformations are a major computational component learned by DNNs and we\nprovide a systematic method to study them.","url_abs":"http://arxiv.org/abs/1807.10589v1","url_pdf":"http://arxiv.org/pdf/1807.10589v1.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":"diverse-feature-visualizations-reveal","repo_url":"https://github.com/sacadena/diverse_feature_vis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.10589","atlas_url":"https://app.syntology.ai/?focus=1807.10589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10589"}},"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/sacadena/diverse_feature_vis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"3ba6aec873833b39","entry":"int_shape","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"pixel-cnn/pixel_cnn_pp/nn.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/pixel_cnn_pp/nn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ba6aec873833b39"}},{"code_sha256_prefix":"919f423798c6a32a","entry":"concat_elu","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"pixel-cnn/pixel_cnn_pp/nn.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/pixel_cnn_pp/nn.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":"919f423798c6a32a"}},{"code_sha256_prefix":"0cb6bf5e8d04ced1","entry":"conv_filter_tile","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"pixel-cnn/utils/plotting.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/utils/plotting.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":"0cb6bf5e8d04ced1"}},{"code_sha256_prefix":"e5e8e8a0eb923ad9","entry":"deprocess_image","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"diverse_vis_functions.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/diverse_vis_functions.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":"e5e8e8a0eb923ad9"}},{"code_sha256_prefix":"6b93fbdaf0e2b9e2","entry":"img_stretch","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"pixel-cnn/utils/plotting.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/utils/plotting.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":"6b93fbdaf0e2b9e2"}},{"code_sha256_prefix":"6c57db0a5a8111ab","entry":"img_tile","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"pixel-cnn/utils/plotting.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/utils/plotting.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":"6c57db0a5a8111ab"}},{"code_sha256_prefix":"ba937f5383eb9016","entry":"log_sum_exp","repo":"sacadena/diverse_feature_vis","repo_kind":"official","path":"pixel-cnn/pixel_cnn_pp/nn.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/pixel_cnn_pp/nn.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":"ba937f5383eb9016"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}