{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JVPGTSVPG5TEGPWDROJJP4MSL4","short_pith_number":"pith:JVPGTSVP","schema_version":"1.0","canonical_sha256":"4d5e69caaf3766433ec38b9297f1925f33db063afc6f00356161eb9941444b43","source":{"kind":"arxiv","id":"2112.14491","version":1},"attestation_state":"computed","paper":{"title":"Two-phase training mitigates class imbalance for camera trap image classification with CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Erfan Ghadery, Farjad Malik, Marie-Francine Moens, Ruben Cartuyvels, Simon Wouters","submitted_at":"2021-12-29T10:47:45Z","abstract_excerpt":"By leveraging deep learning to automatically classify camera trap images, ecologists can monitor biodiversity conservation efforts and the effects of climate change on ecosystems more efficiently. Due to the imbalanced class-distribution of camera trap datasets, current models are biased towards the majority classes. As a result, they obtain good performance for a few majority classes but poor performance for many minority classes. We used two-phase training to increase the performance for these minority classes. We trained, next to a baseline model, four models that implemented a different ve"},"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":"2112.14491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-29T10:47:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ec9ab0ca5a69abf7af27074ac1deaf817db66c87f4f60e2479d1e302928366f","abstract_canon_sha256":"24fb93a87ada44e8fc14791cf688b9b8c6869adacae74563cd4290866eca2bf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:22.956758Z","signature_b64":"wN7o9BYCDFqOQXi22uqz361wxazVkHKURFASptg8sMoWdd3M7jA99y/znSiiWpqu9Tr91a3wRmgZbcGgj4JLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d5e69caaf3766433ec38b9297f1925f33db063afc6f00356161eb9941444b43","last_reissued_at":"2026-07-05T03:44:22.956243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:22.956243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-phase training mitigates class imbalance for camera trap image classification with CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Erfan Ghadery, Farjad Malik, Marie-Francine Moens, Ruben Cartuyvels, Simon Wouters","submitted_at":"2021-12-29T10:47:45Z","abstract_excerpt":"By leveraging deep learning to automatically classify camera trap images, ecologists can monitor biodiversity conservation efforts and the effects of climate change on ecosystems more efficiently. Due to the imbalanced class-distribution of camera trap datasets, current models are biased towards the majority classes. As a result, they obtain good performance for a few majority classes but poor performance for many minority classes. We used two-phase training to increase the performance for these minority classes. We trained, next to a baseline model, four models that implemented a different ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14491","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.14491/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":"2112.14491","created_at":"2026-07-05T03:44:22.956303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.14491v1","created_at":"2026-07-05T03:44:22.956303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.14491","created_at":"2026-07-05T03:44:22.956303+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVPGTSVPG5TE","created_at":"2026-07-05T03:44:22.956303+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVPGTSVPG5TEGPWD","created_at":"2026-07-05T03:44:22.956303+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVPGTSVP","created_at":"2026-07-05T03:44:22.956303+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/JVPGTSVPG5TEGPWDROJJP4MSL4","json":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4.json","graph_json":"https://pith.science/api/pith-number/JVPGTSVPG5TEGPWDROJJP4MSL4/graph.json","events_json":"https://pith.science/api/pith-number/JVPGTSVPG5TEGPWDROJJP4MSL4/events.json","paper":"https://pith.science/paper/JVPGTSVP"},"agent_actions":{"view_html":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4","download_json":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4.json","view_paper":"https://pith.science/paper/JVPGTSVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.14491&json=true","fetch_graph":"https://pith.science/api/pith-number/JVPGTSVPG5TEGPWDROJJP4MSL4/graph.json","fetch_events":"https://pith.science/api/pith-number/JVPGTSVPG5TEGPWDROJJP4MSL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4/action/storage_attestation","attest_author":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4/action/author_attestation","sign_citation":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4/action/citation_signature","submit_replication":"https://pith.science/pith/JVPGTSVPG5TEGPWDROJJP4MSL4/action/replication_record"}},"created_at":"2026-07-05T03:44:22.956303+00:00","updated_at":"2026-07-05T03:44:22.956303+00:00"}