{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YSTBHDXIEDX5VAG3DFNKDAKFJ7","short_pith_number":"pith:YSTBHDXI","schema_version":"1.0","canonical_sha256":"c4a6138ee820efda80db195aa181454fe262be01d27f150ccab6650fc3883739","source":{"kind":"arxiv","id":"1610.06756","version":1},"attestation_state":"computed","paper":{"title":"Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erik Rodner, Joachim Denzler, Marcel Simon, Robert B. Fisher","submitted_at":"2016-10-21T12:14:50Z","abstract_excerpt":"In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to image transformations encountered during wild image capture?; (2) how can we predict CNN sensitivity?; and (3) can we increase the robustness of CNNs with respect to image degradations? To answer the first question, we provide an extensive empirical sensitivity analysis of commonly used CNN architectures (AlexNet, VGG19, GoogleNet) across various types of image "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1610.06756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-10-21T12:14:50Z","cross_cats_sorted":[],"title_canon_sha256":"2d739858399c92d0ba379c2059bf97d82eeee8f6fc90a7f10c67386dd121fb0a","abstract_canon_sha256":"69666b5ee326dda1f3dcf399f8f4173122954b4a2260b4070b9a0c1158e3ab08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:36.800220Z","signature_b64":"VTBJsLAfBG5KEAiv9lFqpveFp5GCithFmHs25tGeWfiMDUpj+0WYk/Cnp1Dt9aO8LgEZL6n8GzvVdUOIsql7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4a6138ee820efda80db195aa181454fe262be01d27f150ccab6650fc3883739","last_reissued_at":"2026-05-18T01:01:36.799567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:36.799567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erik Rodner, Joachim Denzler, Marcel Simon, Robert B. Fisher","submitted_at":"2016-10-21T12:14:50Z","abstract_excerpt":"In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to image transformations encountered during wild image capture?; (2) how can we predict CNN sensitivity?; and (3) can we increase the robustness of CNNs with respect to image degradations? To answer the first question, we provide an extensive empirical sensitivity analysis of commonly used CNN architectures (AlexNet, VGG19, GoogleNet) across various types of image "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.06756","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1610.06756","created_at":"2026-05-18T01:01:36.799689+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.06756v1","created_at":"2026-05-18T01:01:36.799689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.06756","created_at":"2026-05-18T01:01:36.799689+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSTBHDXIEDX5","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSTBHDXIEDX5VAG3","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSTBHDXI","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7","json":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7.json","graph_json":"https://pith.science/api/pith-number/YSTBHDXIEDX5VAG3DFNKDAKFJ7/graph.json","events_json":"https://pith.science/api/pith-number/YSTBHDXIEDX5VAG3DFNKDAKFJ7/events.json","paper":"https://pith.science/paper/YSTBHDXI"},"agent_actions":{"view_html":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7","download_json":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7.json","view_paper":"https://pith.science/paper/YSTBHDXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.06756&json=true","fetch_graph":"https://pith.science/api/pith-number/YSTBHDXIEDX5VAG3DFNKDAKFJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/YSTBHDXIEDX5VAG3DFNKDAKFJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7/action/storage_attestation","attest_author":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7/action/author_attestation","sign_citation":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7/action/citation_signature","submit_replication":"https://pith.science/pith/YSTBHDXIEDX5VAG3DFNKDAKFJ7/action/replication_record"}},"created_at":"2026-05-18T01:01:36.799689+00:00","updated_at":"2026-05-18T01:01:36.799689+00:00"}