{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7FPRI5EM2S2KAUA5NIKSTEPK2V","short_pith_number":"pith:7FPRI5EM","schema_version":"1.0","canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","source":{"kind":"arxiv","id":"2605.14346","version":1},"attestation_state":"computed","paper":{"title":"Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Ma, Ping Qian, Weimin Wang, Yuanhang Yao, Zhu Liu","submitted_at":"2026-05-14T04:12:08Z","abstract_excerpt":"Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T04:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"4afb830fda38fe75a4e703f92785496841b75ebbef869effa29e5d5703c469e7","abstract_canon_sha256":"1d51feb6af4f80b86f7da916ee49def1894888b390c06b8f0d005e9b1e1aca8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:08.127176Z","signature_b64":"6RNoNNS3BnHPiXM+M8X6B7BAZUUHXtH3twjjxuE7q8DarQhQYJOl5XG+ve3Qml+CbcrkMCPYADYwPU3VQFZzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","last_reissued_at":"2026-05-17T23:39:08.126535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:08.126535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Ma, Ping Qian, Weimin Wang, Yuanhang Yao, Zhu Liu","submitted_at":"2026-05-14T04:12:08Z","abstract_excerpt":"Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training... Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a frozen general-purpose VFM can reliably supply semantic priors transferable to infrared small targets via SCAM modulation and bilevel optimization without domain-specific adaptation or overfitting to the training distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hierarchical VFM-driven knowledge distillation method with semantic-conditioned modulation and cluster reweighting stabilizes point-supervised infrared small target detection and improves accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2dfc64c51977f9e2fd4cc20158b156bbb91b576ccde15fc81d3310efdf8b5f09"},"source":{"id":"2605.14346","kind":"arxiv","version":1},"verdict":{"id":"83eec166-015c-4727-bea5-54ce31a9ad45","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:53:14.361858Z","strongest_claim":"We propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training... Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability.","one_line_summary":"A hierarchical VFM-driven knowledge distillation method with semantic-conditioned modulation and cluster reweighting stabilizes point-supervised infrared small target detection and improves accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a frozen general-purpose VFM can reliably supply semantic priors transferable to infrared small targets via SCAM modulation and bilevel optimization without domain-specific adaptation or overfitting to the training distribution.","pith_extraction_headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation."},"references":{"count":23,"sample":[{"doi":"","year":2010,"title":"Anal- ysis of new top-hat transformation and the application for infrared dim small target detection.Pattern Recognition, 43(6):2145–2156,","work_id":"a7776eb3-857e-41eb-a18c-a7e19f693675","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"A local contrast method for small infrared target detection.IEEE Transactions on Geoscience and Remote Sensing, 52(1):574–581,","work_id":"a767532b-4763-40fd-8af9-963fbe5bbc2d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Asymmetric contextual modulation for infrared small target detection","work_id":"ca269583-e519-45a7-97d8-dc1fdfb5c346","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Segment Anything","work_id":"0c3b519e-074e-4112-a638-275301245293","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Dense nested attention network for infrared small target detection.IEEE Transactions on Image Processing, 32:1745–1758,","work_id":"f6ab96a5-2933-40f2-8040-53bf96aae0a9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"275e0220fa717406996fc4c1e2e8c76239f5bcfa3a403bb9bb4214237c669892","internal_anchors":2},"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":"2605.14346","created_at":"2026-05-17T23:39:08.126638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14346v1","created_at":"2026-05-17T23:39:08.126638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14346","created_at":"2026-05-17T23:39:08.126638+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FPRI5EM2S2K","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FPRI5EM2S2KAUA5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FPRI5EM","created_at":"2026-05-18T12:33:37.589309+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/7FPRI5EM2S2KAUA5NIKSTEPK2V","json":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V.json","graph_json":"https://pith.science/api/pith-number/7FPRI5EM2S2KAUA5NIKSTEPK2V/graph.json","events_json":"https://pith.science/api/pith-number/7FPRI5EM2S2KAUA5NIKSTEPK2V/events.json","paper":"https://pith.science/paper/7FPRI5EM"},"agent_actions":{"view_html":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V","download_json":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V.json","view_paper":"https://pith.science/paper/7FPRI5EM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14346&json=true","fetch_graph":"https://pith.science/api/pith-number/7FPRI5EM2S2KAUA5NIKSTEPK2V/graph.json","fetch_events":"https://pith.science/api/pith-number/7FPRI5EM2S2KAUA5NIKSTEPK2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/action/storage_attestation","attest_author":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/action/author_attestation","sign_citation":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/action/citation_signature","submit_replication":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/action/replication_record"}},"created_at":"2026-05-17T23:39:08.126638+00:00","updated_at":"2026-05-17T23:39:08.126638+00:00"}