{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EFRSMTNCAIGCXP4M24HG5I6SVC","short_pith_number":"pith:EFRSMTNC","schema_version":"1.0","canonical_sha256":"2163264da2020c2bbf8cd70e6ea3d2a893d673c1b0d0c72a9aa456b6c441c4bf","source":{"kind":"arxiv","id":"2505.11769","version":1},"attestation_state":"computed","paper":{"title":"Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lae-kyoung Lee, Su-Yong An, Wonjune Kim","submitted_at":"2025-05-17T00:29:17Z","abstract_excerpt":"We report on the application of a high-capacity semantic segmentation pipeline to the GOOSE 2D Semantic Segmentation Challenge for unstructured off-road environments. Using a FlashInternImage-B backbone together with a UPerNet decoder, we adapt established techniques, rather than designing new ones, to the distinctive conditions of off-road scenes. Our training recipe couples strong photometric distortion augmentation (to emulate the wide lighting variations of outdoor terrain) with an Exponential Moving Average (EMA) of weights for better generalization. Using only the GOOSE training dataset,"},"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":"2505.11769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T00:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"ced6622346a6ff050039aa989b7d3eb44e70b186b725a154cdd9127d5624a064","abstract_canon_sha256":"6c54a61fef79488a7d73558683d6735ae34fdebd73421e769e17d84cb895c8c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:26.263294Z","signature_b64":"3V9FCirC7YIUF63h0xqh9AqLZr9lTQTchu1/A2FeUQRDxwOWLrsyKYh7SjSBdQrC1EOyK7jificnaEygi/FTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2163264da2020c2bbf8cd70e6ea3d2a893d673c1b0d0c72a9aa456b6c441c4bf","last_reissued_at":"2026-07-05T11:04:26.262800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:26.262800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lae-kyoung Lee, Su-Yong An, Wonjune Kim","submitted_at":"2025-05-17T00:29:17Z","abstract_excerpt":"We report on the application of a high-capacity semantic segmentation pipeline to the GOOSE 2D Semantic Segmentation Challenge for unstructured off-road environments. Using a FlashInternImage-B backbone together with a UPerNet decoder, we adapt established techniques, rather than designing new ones, to the distinctive conditions of off-road scenes. Our training recipe couples strong photometric distortion augmentation (to emulate the wide lighting variations of outdoor terrain) with an Exponential Moving Average (EMA) of weights for better generalization. Using only the GOOSE training dataset,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11769","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.11769/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":"2505.11769","created_at":"2026-07-05T11:04:26.262864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11769v1","created_at":"2026-07-05T11:04:26.262864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11769","created_at":"2026-07-05T11:04:26.262864+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFRSMTNCAIGC","created_at":"2026-07-05T11:04:26.262864+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFRSMTNCAIGCXP4M","created_at":"2026-07-05T11:04:26.262864+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFRSMTNC","created_at":"2026-07-05T11:04:26.262864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20130","citing_title":"SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC","json":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC.json","graph_json":"https://pith.science/api/pith-number/EFRSMTNCAIGCXP4M24HG5I6SVC/graph.json","events_json":"https://pith.science/api/pith-number/EFRSMTNCAIGCXP4M24HG5I6SVC/events.json","paper":"https://pith.science/paper/EFRSMTNC"},"agent_actions":{"view_html":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC","download_json":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC.json","view_paper":"https://pith.science/paper/EFRSMTNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11769&json=true","fetch_graph":"https://pith.science/api/pith-number/EFRSMTNCAIGCXP4M24HG5I6SVC/graph.json","fetch_events":"https://pith.science/api/pith-number/EFRSMTNCAIGCXP4M24HG5I6SVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC/action/storage_attestation","attest_author":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC/action/author_attestation","sign_citation":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC/action/citation_signature","submit_replication":"https://pith.science/pith/EFRSMTNCAIGCXP4M24HG5I6SVC/action/replication_record"}},"created_at":"2026-07-05T11:04:26.262864+00:00","updated_at":"2026-07-05T11:04:26.262864+00:00"}