{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I7P7UJTF22USGO7HPWQE4JTVIX","short_pith_number":"pith:I7P7UJTF","schema_version":"1.0","canonical_sha256":"47dffa2665d6a9233be77da04e267545d72dc6e3e6158a1e630132e8e1de63f7","source":{"kind":"arxiv","id":"2112.06586","version":3},"attestation_state":"computed","paper":{"title":"Active learning with MaskAL reduces annotation effort for training Mask R-CNN","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boubacar Diallo, Eldert J. van Henten, Frits K. van Evert, Gert Kootstra, Hakim Elchaoui Elghor, Pieter M. Blok","submitted_at":"2021-12-13T12:08:27Z","abstract_excerpt":"The generalisation performance of a convolutional neural network (CNN) is influenced by the quantity, quality, and variety of the training images. Training images must be annotated, and this is time consuming and expensive. The goal of our work was to reduce the number of annotated images needed to train a CNN while maintaining its performance. We hypothesised that the performance of a CNN can be improved faster by ensuring that the set of training images contains a large fraction of hard-to-classify images. The objective of our study was to test this hypothesis with an active learning method "},"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":"2112.06586","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-13T12:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"4acc125b5c87e97230225128ae0d2d0fe419f492901703e57ef695a6eea5df7c","abstract_canon_sha256":"0cdc784c8df0a2a1d4ef10d9208ad22e03a40e7e7b38c7438c313a7326f0ceef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:24.927401Z","signature_b64":"PZZ+z+2rFuVq2el1MO78a/WXtO85+sPW4Ffu5mN23SUFIi24J2OJJMqLagdF3333OeGsw3mh6xwZFkKlhokwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47dffa2665d6a9233be77da04e267545d72dc6e3e6158a1e630132e8e1de63f7","last_reissued_at":"2026-07-05T04:40:24.926914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:24.926914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active learning with MaskAL reduces annotation effort for training Mask R-CNN","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boubacar Diallo, Eldert J. van Henten, Frits K. van Evert, Gert Kootstra, Hakim Elchaoui Elghor, Pieter M. Blok","submitted_at":"2021-12-13T12:08:27Z","abstract_excerpt":"The generalisation performance of a convolutional neural network (CNN) is influenced by the quantity, quality, and variety of the training images. Training images must be annotated, and this is time consuming and expensive. The goal of our work was to reduce the number of annotated images needed to train a CNN while maintaining its performance. We hypothesised that the performance of a CNN can be improved faster by ensuring that the set of training images contains a large fraction of hard-to-classify images. The objective of our study was to test this hypothesis with an active learning method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06586","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.06586/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2112.06586","created_at":"2026-07-05T04:40:24.926972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.06586v3","created_at":"2026-07-05T04:40:24.926972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06586","created_at":"2026-07-05T04:40:24.926972+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7P7UJTF22US","created_at":"2026-07-05T04:40:24.926972+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7P7UJTF22USGO7H","created_at":"2026-07-05T04:40:24.926972+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7P7UJTF","created_at":"2026-07-05T04:40:24.926972+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/I7P7UJTF22USGO7HPWQE4JTVIX","json":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX.json","graph_json":"https://pith.science/api/pith-number/I7P7UJTF22USGO7HPWQE4JTVIX/graph.json","events_json":"https://pith.science/api/pith-number/I7P7UJTF22USGO7HPWQE4JTVIX/events.json","paper":"https://pith.science/paper/I7P7UJTF"},"agent_actions":{"view_html":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX","download_json":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX.json","view_paper":"https://pith.science/paper/I7P7UJTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.06586&json=true","fetch_graph":"https://pith.science/api/pith-number/I7P7UJTF22USGO7HPWQE4JTVIX/graph.json","fetch_events":"https://pith.science/api/pith-number/I7P7UJTF22USGO7HPWQE4JTVIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX/action/storage_attestation","attest_author":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX/action/author_attestation","sign_citation":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX/action/citation_signature","submit_replication":"https://pith.science/pith/I7P7UJTF22USGO7HPWQE4JTVIX/action/replication_record"}},"created_at":"2026-07-05T04:40:24.926972+00:00","updated_at":"2026-07-05T04:40:24.926972+00:00"}