{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NLGNPQVVIN6ISFLWLOJZBO7AUY","short_pith_number":"pith:NLGNPQVV","schema_version":"1.0","canonical_sha256":"6accd7c2b5437c8915765b9390bbe0a60e3610269e4c1f4c3d316811aef6f2b5","source":{"kind":"arxiv","id":"2303.17937","version":1},"attestation_state":"computed","paper":{"title":"STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kui Jia, Xun Xu, Yijin Chen, Yongyi Su","submitted_at":"2023-03-31T10:04:44Z","abstract_excerpt":"Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is often unpredictable until inference stage. This motivates us to explore adapting an object detection model at test-time, a.k.a. test-time adaptation (TTA). In this work, we approach test-time adaptive object detection (TTAOD) from two perspective. First, we adopt a self-training paradigm to generate pseudo labeled objects with an exponential moving average mo"},"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":"2303.17937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-31T10:04:44Z","cross_cats_sorted":[],"title_canon_sha256":"afcda83a35027a695680413c5607518107ca9a996c6253c9cec03f7cf02c15ab","abstract_canon_sha256":"f917bdaa6c6b4acea941bf3dd57654d3c805ff71e70b191ba6a1d90f47e84279"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:47.951433Z","signature_b64":"btS9wLbi3ONt6QSZYx/qHqOoR5VnIaietX/04J+VNf2I2XI48J68LUnfx4I/uEqIiFUI7DUVy0iD16etqkNIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6accd7c2b5437c8915765b9390bbe0a60e3610269e4c1f4c3d316811aef6f2b5","last_reissued_at":"2026-07-05T05:56:47.950888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:47.950888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kui Jia, Xun Xu, Yijin Chen, Yongyi Su","submitted_at":"2023-03-31T10:04:44Z","abstract_excerpt":"Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is often unpredictable until inference stage. This motivates us to explore adapting an object detection model at test-time, a.k.a. test-time adaptation (TTA). In this work, we approach test-time adaptive object detection (TTAOD) from two perspective. First, we adopt a self-training paradigm to generate pseudo labeled objects with an exponential moving average mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17937","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/2303.17937/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":"2303.17937","created_at":"2026-07-05T05:56:47.950947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17937v1","created_at":"2026-07-05T05:56:47.950947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17937","created_at":"2026-07-05T05:56:47.950947+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLGNPQVVIN6I","created_at":"2026-07-05T05:56:47.950947+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLGNPQVVIN6ISFLW","created_at":"2026-07-05T05:56:47.950947+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLGNPQVV","created_at":"2026-07-05T05:56:47.950947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04531","citing_title":"Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY","json":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY.json","graph_json":"https://pith.science/api/pith-number/NLGNPQVVIN6ISFLWLOJZBO7AUY/graph.json","events_json":"https://pith.science/api/pith-number/NLGNPQVVIN6ISFLWLOJZBO7AUY/events.json","paper":"https://pith.science/paper/NLGNPQVV"},"agent_actions":{"view_html":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY","download_json":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY.json","view_paper":"https://pith.science/paper/NLGNPQVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17937&json=true","fetch_graph":"https://pith.science/api/pith-number/NLGNPQVVIN6ISFLWLOJZBO7AUY/graph.json","fetch_events":"https://pith.science/api/pith-number/NLGNPQVVIN6ISFLWLOJZBO7AUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY/action/storage_attestation","attest_author":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY/action/author_attestation","sign_citation":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY/action/citation_signature","submit_replication":"https://pith.science/pith/NLGNPQVVIN6ISFLWLOJZBO7AUY/action/replication_record"}},"created_at":"2026-07-05T05:56:47.950947+00:00","updated_at":"2026-07-05T05:56:47.950947+00:00"}