{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L46T3OLYTXDOOTXABZAATGBSZI","short_pith_number":"pith:L46T3OLY","schema_version":"1.0","canonical_sha256":"5f3d3db9789dc6e74ee00e40099832ca1c749b5b6d412fce4cc0297e63746ac0","source":{"kind":"arxiv","id":"2305.03048","version":2},"attestation_state":"computed","paper":{"title":"Personalize Segment Anything Model with One Shot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hao Dong, Hongsheng Li, Junting Pan, Peng Gao, Renrui Zhang, Shilin Yan, Xianzheng Ma, Zhengkai Jiang, Ziyu Guo","submitted_at":"2023-05-04T17:59:36Z","abstract_excerpt":"Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models. Despite the generality, customizing SAM for specific visual concepts without man-powered prompting is under explored, e.g., automatically segmenting your pet dog in different images. In this paper, we propose a training-free Personalization approach for SAM, termed as PerSAM. Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior, and segments it within other images or video"},"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":"2305.03048","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T17:59:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"a675ba384390e616b73bcc2ab3e8a86bb904fd212aab478dc381abb2d2c6ef9a","abstract_canon_sha256":"aee10e2e8065e21666a78c04014dbb26da838be49d14caa6ac7726f4298ed3bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:53.431110Z","signature_b64":"Aea8wAuc5Yo8s+Df3hBawR/Ze6Y3kmg0h9c5ypmOE4Yx9SkdwxEd+0YZv8Q0pfEzSF/Q5kfOXzuR5s9CARseBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f3d3db9789dc6e74ee00e40099832ca1c749b5b6d412fce4cc0297e63746ac0","last_reissued_at":"2026-07-05T06:56:53.430599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:53.430599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalize Segment Anything Model with One Shot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hao Dong, Hongsheng Li, Junting Pan, Peng Gao, Renrui Zhang, Shilin Yan, Xianzheng Ma, Zhengkai Jiang, Ziyu Guo","submitted_at":"2023-05-04T17:59:36Z","abstract_excerpt":"Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models. Despite the generality, customizing SAM for specific visual concepts without man-powered prompting is under explored, e.g., automatically segmenting your pet dog in different images. In this paper, we propose a training-free Personalization approach for SAM, termed as PerSAM. Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior, and segments it within other images or video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03048","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/2305.03048/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":"2305.03048","created_at":"2026-07-05T06:56:53.430673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03048v2","created_at":"2026-07-05T06:56:53.430673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03048","created_at":"2026-07-05T06:56:53.430673+00:00"},{"alias_kind":"pith_short_12","alias_value":"L46T3OLYTXDO","created_at":"2026-07-05T06:56:53.430673+00:00"},{"alias_kind":"pith_short_16","alias_value":"L46T3OLYTXDOOTXA","created_at":"2026-07-05T06:56:53.430673+00:00"},{"alias_kind":"pith_short_8","alias_value":"L46T3OLY","created_at":"2026-07-05T06:56:53.430673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05253","citing_title":"Repurposing CLIP to Localize at Pixel Level","ref_index":6,"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24296","citing_title":"Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation","ref_index":46,"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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09303","citing_title":"Reason Twice: Segmentation via Candidate Discovery and Comparative Reasoning","ref_index":93,"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":78,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04282","citing_title":"FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs","ref_index":49,"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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20436","citing_title":"Lighting-aware Unified Model for Instance Segmentation","ref_index":31,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25730","citing_title":"DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30168","citing_title":"OmniCD: A Foundational Framework for Remote Sensing Image Change Detection Guided by Multimodal Semantics","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03088","citing_title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20436","citing_title":"Lighting-aware Unified Model for Instance Segmentation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":170,"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":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27494","citing_title":"Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11441","citing_title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07901","citing_title":"PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI","json":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI.json","graph_json":"https://pith.science/api/pith-number/L46T3OLYTXDOOTXABZAATGBSZI/graph.json","events_json":"https://pith.science/api/pith-number/L46T3OLYTXDOOTXABZAATGBSZI/events.json","paper":"https://pith.science/paper/L46T3OLY"},"agent_actions":{"view_html":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI","download_json":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI.json","view_paper":"https://pith.science/paper/L46T3OLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03048&json=true","fetch_graph":"https://pith.science/api/pith-number/L46T3OLYTXDOOTXABZAATGBSZI/graph.json","fetch_events":"https://pith.science/api/pith-number/L46T3OLYTXDOOTXABZAATGBSZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI/action/storage_attestation","attest_author":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI/action/author_attestation","sign_citation":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI/action/citation_signature","submit_replication":"https://pith.science/pith/L46T3OLYTXDOOTXABZAATGBSZI/action/replication_record"}},"created_at":"2026-07-05T06:56:53.430673+00:00","updated_at":"2026-07-05T06:56:53.430673+00:00"}