{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RIF6ICHTXLXQDP347HVAIPWR2Z","short_pith_number":"pith:RIF6ICHT","schema_version":"1.0","canonical_sha256":"8a0be408f3baef01bf7cf9ea043ed1d667ffbb4d6cf6986f6db8e2f28372fbf9","source":{"kind":"arxiv","id":"2104.01538","version":3},"attestation_state":"computed","paper":{"title":"Hypercorrelation Squeeze for Few-Shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahyun Kang, Juhong Min, Minsu Cho","submitted_at":"2021-04-04T05:27:13Z","abstract_excerpt":"Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. It extracts diverse features from different levels of intermediate convolutional layers and constructs a collection of 4D"},"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":"2104.01538","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-04T05:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"51f2ec8915fde0367794d88e3fc1e7b2ba199c96b2c1e6ec9042d23a49bf6724","abstract_canon_sha256":"4c2543eef7a50941755f029bb3add0e8e6d40e1958fe9c773d20d1831032d55a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:45.498181Z","signature_b64":"azubd+tyTVXs3w04X4FOr9jZATclEn5cFiEtc8pET9lLggHg43wU5QtX6unOWlQ1ZO6y6AKfYoYGOhnlOgI0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a0be408f3baef01bf7cf9ea043ed1d667ffbb4d6cf6986f6db8e2f28372fbf9","last_reissued_at":"2026-07-05T03:22:45.497749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:45.497749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypercorrelation Squeeze for Few-Shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahyun Kang, Juhong Min, Minsu Cho","submitted_at":"2021-04-04T05:27:13Z","abstract_excerpt":"Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. It extracts diverse features from different levels of intermediate convolutional layers and constructs a collection of 4D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01538","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/2104.01538/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":"2104.01538","created_at":"2026-07-05T03:22:45.497815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01538v3","created_at":"2026-07-05T03:22:45.497815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01538","created_at":"2026-07-05T03:22:45.497815+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIF6ICHTXLXQ","created_at":"2026-07-05T03:22:45.497815+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIF6ICHTXLXQDP34","created_at":"2026-07-05T03:22:45.497815+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIF6ICHT","created_at":"2026-07-05T03:22:45.497815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09562","citing_title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z","json":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z.json","graph_json":"https://pith.science/api/pith-number/RIF6ICHTXLXQDP347HVAIPWR2Z/graph.json","events_json":"https://pith.science/api/pith-number/RIF6ICHTXLXQDP347HVAIPWR2Z/events.json","paper":"https://pith.science/paper/RIF6ICHT"},"agent_actions":{"view_html":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z","download_json":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z.json","view_paper":"https://pith.science/paper/RIF6ICHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01538&json=true","fetch_graph":"https://pith.science/api/pith-number/RIF6ICHTXLXQDP347HVAIPWR2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/RIF6ICHTXLXQDP347HVAIPWR2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z/action/storage_attestation","attest_author":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z/action/author_attestation","sign_citation":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z/action/citation_signature","submit_replication":"https://pith.science/pith/RIF6ICHTXLXQDP347HVAIPWR2Z/action/replication_record"}},"created_at":"2026-07-05T03:22:45.497815+00:00","updated_at":"2026-07-05T03:22:45.497815+00:00"}