{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YA2M2EK6D2LFDWRXLZL7NP7EIH","short_pith_number":"pith:YA2M2EK6","schema_version":"1.0","canonical_sha256":"c034cd115e1e9651da375e57f6bfe441e56f02f4aab9295487f86befcc89bb89","source":{"kind":"arxiv","id":"1704.02966","version":1},"attestation_state":"computed","paper":{"title":"Loss Max-Pooling for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Gerhard Neuhold, Peter Kontschieder, Samuel Rota Bul\\`o","submitted_at":"2017-04-10T17:44:33Z","abstract_excerpt":"We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories comprising the majority of data and consequently biasing the classifiers towards them. Our method adaptively re-weights the contributions of each pixel based on their observed losses, targeting under-performing classification results as often encountered for under-represented object cl"},"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":"1704.02966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T17:44:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e094bdbd4734bbbeeec1b08807d8c6654f9ac3f83d44651efb2d91f6018c091d","abstract_canon_sha256":"45449be11d690f0b081ab2f58d099897ce421e731a6628010d520b30e957d89b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:43.515265Z","signature_b64":"hUW7cCkbR4FzuwawLCn1v/bwuRxiymrjONp4E9wUvxcIlBrtySwdFYf4v9HxVNcyUK5Dvn4TnzeEEcvNclCvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c034cd115e1e9651da375e57f6bfe441e56f02f4aab9295487f86befcc89bb89","last_reissued_at":"2026-05-18T00:46:43.514536Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:43.514536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loss Max-Pooling for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Gerhard Neuhold, Peter Kontschieder, Samuel Rota Bul\\`o","submitted_at":"2017-04-10T17:44:33Z","abstract_excerpt":"We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories comprising the majority of data and consequently biasing the classifiers towards them. Our method adaptively re-weights the contributions of each pixel based on their observed losses, targeting under-performing classification results as often encountered for under-represented object cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02966","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":"1704.02966","created_at":"2026-05-18T00:46:43.514657+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02966v1","created_at":"2026-05-18T00:46:43.514657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02966","created_at":"2026-05-18T00:46:43.514657+00:00"},{"alias_kind":"pith_short_12","alias_value":"YA2M2EK6D2LF","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YA2M2EK6D2LFDWRX","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YA2M2EK6","created_at":"2026-05-18T12:31:56.362134+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/YA2M2EK6D2LFDWRXLZL7NP7EIH","json":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH.json","graph_json":"https://pith.science/api/pith-number/YA2M2EK6D2LFDWRXLZL7NP7EIH/graph.json","events_json":"https://pith.science/api/pith-number/YA2M2EK6D2LFDWRXLZL7NP7EIH/events.json","paper":"https://pith.science/paper/YA2M2EK6"},"agent_actions":{"view_html":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH","download_json":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH.json","view_paper":"https://pith.science/paper/YA2M2EK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02966&json=true","fetch_graph":"https://pith.science/api/pith-number/YA2M2EK6D2LFDWRXLZL7NP7EIH/graph.json","fetch_events":"https://pith.science/api/pith-number/YA2M2EK6D2LFDWRXLZL7NP7EIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH/action/storage_attestation","attest_author":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH/action/author_attestation","sign_citation":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH/action/citation_signature","submit_replication":"https://pith.science/pith/YA2M2EK6D2LFDWRXLZL7NP7EIH/action/replication_record"}},"created_at":"2026-05-18T00:46:43.514657+00:00","updated_at":"2026-05-18T00:46:43.514657+00:00"}