{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VTAGMBVKJ4GMTKMEVBXOP7K2GW","short_pith_number":"pith:VTAGMBVK","schema_version":"1.0","canonical_sha256":"acc06606aa4f0cc9a984a86ee7fd5a35a127017f4e271c5576cdb4c6c83b7458","source":{"kind":"arxiv","id":"1709.03410","version":1},"attestation_state":"computed","paper":{"title":"One-Shot Learning for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amirreza Shaban, Byron Boots, Irfan Essa, Shray Bansal, Zhen Liu","submitted_at":"2017-09-11T14:34:58Z","abstract_excerpt":"Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images, produces parameters for a Fully Convolutional Network (FCN). We use this FCN to perform dense pixel-level prediction on a test image for the new semantic class. Our architecture shows a 25% relative meanIoU improvement compared to the best baseline methods for one-shot segmentation on unseen classes in the PASCAL VOC 2012 dataset and is at least 3 times faster."},"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":"1709.03410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-11T14:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"59d69aa9b4b48b0f1aa6a5c07158d90502f0ee40c869b1d30d291da7ff88c45d","abstract_canon_sha256":"f2ad45d58a7d7efacd4f05e84a16e1d8d0c49ed6aebd4da03103ed04b0f514d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:38.490294Z","signature_b64":"sXFe0/5Mbys4xBRNoGvjyluduID3AiAPpb0lZRcIvD0NXPuTDVWuTV/DECzkxZkmXUgbEMbCaM8I1C1hGX/wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc06606aa4f0cc9a984a86ee7fd5a35a127017f4e271c5576cdb4c6c83b7458","last_reissued_at":"2026-05-18T00:35:38.489622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:38.489622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot Learning for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amirreza Shaban, Byron Boots, Irfan Essa, Shray Bansal, Zhen Liu","submitted_at":"2017-09-11T14:34:58Z","abstract_excerpt":"Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images, produces parameters for a Fully Convolutional Network (FCN). We use this FCN to perform dense pixel-level prediction on a test image for the new semantic class. Our architecture shows a 25% relative meanIoU improvement compared to the best baseline methods for one-shot segmentation on unseen classes in the PASCAL VOC 2012 dataset and is at least 3 times faster."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03410","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":"1709.03410","created_at":"2026-05-18T00:35:38.489736+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03410v1","created_at":"2026-05-18T00:35:38.489736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03410","created_at":"2026-05-18T00:35:38.489736+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTAGMBVKJ4GM","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTAGMBVKJ4GMTKME","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTAGMBVK","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17904","citing_title":"Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03134","citing_title":"SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12113","citing_title":"PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW","json":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW.json","graph_json":"https://pith.science/api/pith-number/VTAGMBVKJ4GMTKMEVBXOP7K2GW/graph.json","events_json":"https://pith.science/api/pith-number/VTAGMBVKJ4GMTKMEVBXOP7K2GW/events.json","paper":"https://pith.science/paper/VTAGMBVK"},"agent_actions":{"view_html":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW","download_json":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW.json","view_paper":"https://pith.science/paper/VTAGMBVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03410&json=true","fetch_graph":"https://pith.science/api/pith-number/VTAGMBVKJ4GMTKMEVBXOP7K2GW/graph.json","fetch_events":"https://pith.science/api/pith-number/VTAGMBVKJ4GMTKMEVBXOP7K2GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW/action/storage_attestation","attest_author":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW/action/author_attestation","sign_citation":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW/action/citation_signature","submit_replication":"https://pith.science/pith/VTAGMBVKJ4GMTKMEVBXOP7K2GW/action/replication_record"}},"created_at":"2026-05-18T00:35:38.489736+00:00","updated_at":"2026-05-18T00:35:38.489736+00:00"}