{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6ALQJVDI2KW6P4UZUG6FG3ACU6","short_pith_number":"pith:6ALQJVDI","schema_version":"1.0","canonical_sha256":"f01704d468d2ade7f299a1bc536c02a7926bdd12ff6eebd4c07cbb708f18ced5","source":{"kind":"arxiv","id":"2309.03179","version":4},"attestation_state":"computed","paper":{"title":"SLiMe: Segment Like Me","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Sanghi, Aliasghar Khani, Ali Mahdavi Amiri, Ghassan Hamarneh, Saeid Asgari Taghanaki","submitted_at":"2023-09-06T17:39:05Z","abstract_excerpt":"Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we explore leveraging these extensive vision-language models for segmenting images at any desired granularity using as few as one annotated sample by proposing SLiMe. SLiMe frames this problem as an optimization task. Specifically, given a single training image and its segmentation mask, we first extract attention maps, including our novel \"weighted accumulate"},"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":"2309.03179","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T17:39:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f22dc60143884e0991387ef4e88b47dfe41dd5ae277151f4893be19b58caab5","abstract_canon_sha256":"138f5fe20a160ff03a694c3463f112a802f839269036fad8e083e5d6b3d09613"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:59.048938Z","signature_b64":"uNBLIhAKnQiM4ZBfG4drhsA6AH/pF8iOsW3aK/LGPpWw83G1HcYDEx3layqKCWqs8BGClTjdeK4gdEJwvI4uCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01704d468d2ade7f299a1bc536c02a7926bdd12ff6eebd4c07cbb708f18ced5","last_reissued_at":"2026-07-05T07:55:59.048426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:59.048426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLiMe: Segment Like Me","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Sanghi, Aliasghar Khani, Ali Mahdavi Amiri, Ghassan Hamarneh, Saeid Asgari Taghanaki","submitted_at":"2023-09-06T17:39:05Z","abstract_excerpt":"Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we explore leveraging these extensive vision-language models for segmenting images at any desired granularity using as few as one annotated sample by proposing SLiMe. SLiMe frames this problem as an optimization task. Specifically, given a single training image and its segmentation mask, we first extract attention maps, including our novel \"weighted accumulate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03179","kind":"arxiv","version":4},"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/2309.03179/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":"2309.03179","created_at":"2026-07-05T07:55:59.048496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03179v4","created_at":"2026-07-05T07:55:59.048496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03179","created_at":"2026-07-05T07:55:59.048496+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ALQJVDI2KW6","created_at":"2026-07-05T07:55:59.048496+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ALQJVDI2KW6P4UZ","created_at":"2026-07-05T07:55:59.048496+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ALQJVDI","created_at":"2026-07-05T07:55:59.048496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26933","citing_title":"Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6","json":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6.json","graph_json":"https://pith.science/api/pith-number/6ALQJVDI2KW6P4UZUG6FG3ACU6/graph.json","events_json":"https://pith.science/api/pith-number/6ALQJVDI2KW6P4UZUG6FG3ACU6/events.json","paper":"https://pith.science/paper/6ALQJVDI"},"agent_actions":{"view_html":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6","download_json":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6.json","view_paper":"https://pith.science/paper/6ALQJVDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03179&json=true","fetch_graph":"https://pith.science/api/pith-number/6ALQJVDI2KW6P4UZUG6FG3ACU6/graph.json","fetch_events":"https://pith.science/api/pith-number/6ALQJVDI2KW6P4UZUG6FG3ACU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6/action/storage_attestation","attest_author":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6/action/author_attestation","sign_citation":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6/action/citation_signature","submit_replication":"https://pith.science/pith/6ALQJVDI2KW6P4UZUG6FG3ACU6/action/replication_record"}},"created_at":"2026-07-05T07:55:59.048496+00:00","updated_at":"2026-07-05T07:55:59.048496+00:00"}