{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XYZMR3SMEL5IV43KIWB3Q2CC5V","short_pith_number":"pith:XYZMR3SM","schema_version":"1.0","canonical_sha256":"be32c8ee4c22fa8af36a4583b86842ed45a371e7adf617ca3177698dabc0e5a3","source":{"kind":"arxiv","id":"2402.18698","version":2},"attestation_state":"computed","paper":{"title":"Spatial Coherence Loss: All Objects Matter in Salient and Camouflaged Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Choy, Sina Farsiu, Ziyun Yang","submitted_at":"2024-02-28T20:27:49Z","abstract_excerpt":"Generic object detection is a category-independent task that relies on accurate modeling of objectness. We show that for accurate semantic analysis, the network needs to learn all object-level predictions that appear at any stage of learning, including the pre-defined ground truth (GT) objects and the ambiguous decoy objects that the network misidentifies as foreground. Yet, most relevant models focused mainly on improving the learning of the GT objects. A few methods that consider decoy objects utilize loss functions that only focus on the single-response, i.e., the loss response of a single "},"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":"2402.18698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T20:27:49Z","cross_cats_sorted":[],"title_canon_sha256":"e4101bf5107380f4bd69973ebddaacbb43f9b8231673a9658293da8a01a0ef00","abstract_canon_sha256":"c0f368ba3e4fd713055869fa615bdf53ba5fea059477dd98daaef2806635eab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:51.509897Z","signature_b64":"ccjab6rCADiMALRVxPIfhH1yEKya5Es/ItwUMn3LpuxXgITwwZW6pei+0gSXdeDSPrC/j/NX4SsS7vT5pShnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be32c8ee4c22fa8af36a4583b86842ed45a371e7adf617ca3177698dabc0e5a3","last_reissued_at":"2026-07-05T08:44:51.509310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:51.509310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Coherence Loss: All Objects Matter in Salient and Camouflaged Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Choy, Sina Farsiu, Ziyun Yang","submitted_at":"2024-02-28T20:27:49Z","abstract_excerpt":"Generic object detection is a category-independent task that relies on accurate modeling of objectness. We show that for accurate semantic analysis, the network needs to learn all object-level predictions that appear at any stage of learning, including the pre-defined ground truth (GT) objects and the ambiguous decoy objects that the network misidentifies as foreground. Yet, most relevant models focused mainly on improving the learning of the GT objects. A few methods that consider decoy objects utilize loss functions that only focus on the single-response, i.e., the loss response of a single "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18698","kind":"arxiv","version":2},"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/2402.18698/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":"2402.18698","created_at":"2026-07-05T08:44:51.509388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18698v2","created_at":"2026-07-05T08:44:51.509388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18698","created_at":"2026-07-05T08:44:51.509388+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYZMR3SMEL5I","created_at":"2026-07-05T08:44:51.509388+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYZMR3SMEL5IV43K","created_at":"2026-07-05T08:44:51.509388+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYZMR3SM","created_at":"2026-07-05T08:44:51.509388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25385","citing_title":"Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V","json":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V.json","graph_json":"https://pith.science/api/pith-number/XYZMR3SMEL5IV43KIWB3Q2CC5V/graph.json","events_json":"https://pith.science/api/pith-number/XYZMR3SMEL5IV43KIWB3Q2CC5V/events.json","paper":"https://pith.science/paper/XYZMR3SM"},"agent_actions":{"view_html":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V","download_json":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V.json","view_paper":"https://pith.science/paper/XYZMR3SM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18698&json=true","fetch_graph":"https://pith.science/api/pith-number/XYZMR3SMEL5IV43KIWB3Q2CC5V/graph.json","fetch_events":"https://pith.science/api/pith-number/XYZMR3SMEL5IV43KIWB3Q2CC5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V/action/storage_attestation","attest_author":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V/action/author_attestation","sign_citation":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V/action/citation_signature","submit_replication":"https://pith.science/pith/XYZMR3SMEL5IV43KIWB3Q2CC5V/action/replication_record"}},"created_at":"2026-07-05T08:44:51.509388+00:00","updated_at":"2026-07-05T08:44:51.509388+00:00"}