{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FRKNMCFE4WZJGOR7AR6KQXMMBU","short_pith_number":"pith:FRKNMCFE","schema_version":"1.0","canonical_sha256":"2c54d608a4e5b2933a3f047ca85d8c0d03cff5751d22b4ad11af82360afdd150","source":{"kind":"arxiv","id":"2305.13310","version":2},"attestation_state":"computed","paper":{"title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Hengtao Li, Muzhi Zhu, Xinlong Wang, Yang Liu","submitted_at":"2023-05-22T17:59:43Z","abstract_excerpt":"Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. However, unlike large language models that excel at directly tackling various language tasks, vision foundation models require a task-specific model structure followed by fine-tuning on specific tasks. In this work, we present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks. Matcher can segment anything by using an in-context example without training. Additionally, we design three effective c"},"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":"2305.13310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T17:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"6f45acbe61f39eafb9cc655b31026358877eff6281470dd0ee4a8bf7496e0600","abstract_canon_sha256":"eccfab5fcd6d8f82ad0a1fde01304d0d3a28592a76fa4b149b43504682e539a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:19.029649Z","signature_b64":"QZZSA/xyEvll3smK0VXodKyDZnn4O6kh9qvRi0qq7AMlxdeCnCW2A7eRhBbX7ELoNgyXHBJMfK87P7cuLKtGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c54d608a4e5b2933a3f047ca85d8c0d03cff5751d22b4ad11af82360afdd150","last_reissued_at":"2026-07-05T07:35:19.029232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:19.029232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Hengtao Li, Muzhi Zhu, Xinlong Wang, Yang Liu","submitted_at":"2023-05-22T17:59:43Z","abstract_excerpt":"Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. However, unlike large language models that excel at directly tackling various language tasks, vision foundation models require a task-specific model structure followed by fine-tuning on specific tasks. In this work, we present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks. Matcher can segment anything by using an in-context example without training. Additionally, we design three effective c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13310","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/2305.13310/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":"2305.13310","created_at":"2026-07-05T07:35:19.029287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13310v2","created_at":"2026-07-05T07:35:19.029287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13310","created_at":"2026-07-05T07:35:19.029287+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRKNMCFE4WZJ","created_at":"2026-07-05T07:35:19.029287+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRKNMCFE4WZJGOR7","created_at":"2026-07-05T07:35:19.029287+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRKNMCFE","created_at":"2026-07-05T07:35:19.029287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05253","citing_title":"Repurposing CLIP to Localize at Pixel Level","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24297","citing_title":"Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26711","citing_title":"Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09670","citing_title":"Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07965","citing_title":"Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07953","citing_title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26711","citing_title":"Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31136","citing_title":"FROST: Training-Free Few-Shot Segmentation with Frozen Features and Nonparametric Statistics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28920","citing_title":"ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07436","citing_title":"RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp Segmentation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04501","citing_title":"Example-Based Object Detection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU","json":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU.json","graph_json":"https://pith.science/api/pith-number/FRKNMCFE4WZJGOR7AR6KQXMMBU/graph.json","events_json":"https://pith.science/api/pith-number/FRKNMCFE4WZJGOR7AR6KQXMMBU/events.json","paper":"https://pith.science/paper/FRKNMCFE"},"agent_actions":{"view_html":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU","download_json":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU.json","view_paper":"https://pith.science/paper/FRKNMCFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13310&json=true","fetch_graph":"https://pith.science/api/pith-number/FRKNMCFE4WZJGOR7AR6KQXMMBU/graph.json","fetch_events":"https://pith.science/api/pith-number/FRKNMCFE4WZJGOR7AR6KQXMMBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU/action/storage_attestation","attest_author":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU/action/author_attestation","sign_citation":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU/action/citation_signature","submit_replication":"https://pith.science/pith/FRKNMCFE4WZJGOR7AR6KQXMMBU/action/replication_record"}},"created_at":"2026-07-05T07:35:19.029287+00:00","updated_at":"2026-07-05T07:35:19.029287+00:00"}