{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VNGN3AMK35WOCBCLWEX5E2G2EC","short_pith_number":"pith:VNGN3AMK","schema_version":"1.0","canonical_sha256":"ab4cdd818adf6ce1044bb12fd268da208f75446dadf4bfd903010a7c59f02beb","source":{"kind":"arxiv","id":"2410.13582","version":1},"attestation_state":"computed","paper":{"title":"Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nikolaos-Antonios Ypsilantis, Ond\\v{r}ej Chum","submitted_at":"2024-10-17T14:16:45Z","abstract_excerpt":"This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are exploited: ImageNet classification-trained ViT, whose features are used to estimate rough object localization through intra-class token relevance, and a self-supervised DINO-ViT for intra-image token relevance. On recent challenging benchmarks, the method achieves state-of-the-art performance among methods trained with the same level of supervision (image labels) "},"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":"2410.13582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T14:16:45Z","cross_cats_sorted":[],"title_canon_sha256":"539a429bcc7c06fc6cb91351178b33a8fb179b7e7c010b23903f25d74bb5e5c5","abstract_canon_sha256":"1c662eb836be89e6467ea17b4d1d94133006c8b05483414fc54f08298927918f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:03.012849Z","signature_b64":"5WRaS726PlaLC05N70NYDpiU78mZ0qrKYKwv2ZIVBGj8IxxWZCA28HrMpTbwXknt9VqdnuU1mM65XguMwGVqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab4cdd818adf6ce1044bb12fd268da208f75446dadf4bfd903010a7c59f02beb","last_reissued_at":"2026-07-05T09:22:03.012428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:03.012428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nikolaos-Antonios Ypsilantis, Ond\\v{r}ej Chum","submitted_at":"2024-10-17T14:16:45Z","abstract_excerpt":"This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are exploited: ImageNet classification-trained ViT, whose features are used to estimate rough object localization through intra-class token relevance, and a self-supervised DINO-ViT for intra-image token relevance. On recent challenging benchmarks, the method achieves state-of-the-art performance among methods trained with the same level of supervision (image labels) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13582","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/2410.13582/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":"2410.13582","created_at":"2026-07-05T09:22:03.012484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13582v1","created_at":"2026-07-05T09:22:03.012484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13582","created_at":"2026-07-05T09:22:03.012484+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNGN3AMK35WO","created_at":"2026-07-05T09:22:03.012484+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNGN3AMK35WOCBCL","created_at":"2026-07-05T09:22:03.012484+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNGN3AMK","created_at":"2026-07-05T09:22:03.012484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC","json":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC.json","graph_json":"https://pith.science/api/pith-number/VNGN3AMK35WOCBCLWEX5E2G2EC/graph.json","events_json":"https://pith.science/api/pith-number/VNGN3AMK35WOCBCLWEX5E2G2EC/events.json","paper":"https://pith.science/paper/VNGN3AMK"},"agent_actions":{"view_html":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC","download_json":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC.json","view_paper":"https://pith.science/paper/VNGN3AMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13582&json=true","fetch_graph":"https://pith.science/api/pith-number/VNGN3AMK35WOCBCLWEX5E2G2EC/graph.json","fetch_events":"https://pith.science/api/pith-number/VNGN3AMK35WOCBCLWEX5E2G2EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC/action/storage_attestation","attest_author":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC/action/author_attestation","sign_citation":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC/action/citation_signature","submit_replication":"https://pith.science/pith/VNGN3AMK35WOCBCLWEX5E2G2EC/action/replication_record"}},"created_at":"2026-07-05T09:22:03.012484+00:00","updated_at":"2026-07-05T09:22:03.012484+00:00"}