{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B7GM7PRF7CFCI57OIXV4R6ZON5","short_pith_number":"pith:B7GM7PRF","schema_version":"1.0","canonical_sha256":"0fcccfbe25f88a2477ee45ebc8fb2e6f4c4b5339d12c1293ac3a251762fd9096","source":{"kind":"arxiv","id":"2303.09813","version":1},"attestation_state":"computed","paper":{"title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaofan Ma, Chen Ju, Fei Zhang, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yuhuan Yang, Yu Wang","submitted_at":"2023-03-17T07:47:55Z","abstract_excerpt":"Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this paper, we propose to exploit such knowledgeable diffusion models for mainstream discriminative tasks, i.e., unsupervised object discovery: saliency segmentation and object localization. However, the challenges exist as there is one structural difference between generative and discriminative models, which limits the direct use. Besides, the lack of explicitly la"},"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":"2303.09813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T07:47:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af9bc64932d9a40b51bfbcb8632a597358408993e28f53a3fb7b3784ea339e24","abstract_canon_sha256":"7370d15d58aca29c964271e9696ae1ed11342229e075aa4cf7309606c044a0d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:11.051948Z","signature_b64":"vxTpCrKN3Ia7z0m00S6/f+NBwh1GO3NFiLcYx6Iy/iOWyz2LWgqmI8CvP+wcDEOhAQOBf5KNPRcFv5PZMtlkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fcccfbe25f88a2477ee45ebc8fb2e6f4c4b5339d12c1293ac3a251762fd9096","last_reissued_at":"2026-07-05T05:52:11.051478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:11.051478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaofan Ma, Chen Ju, Fei Zhang, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yuhuan Yang, Yu Wang","submitted_at":"2023-03-17T07:47:55Z","abstract_excerpt":"Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this paper, we propose to exploit such knowledgeable diffusion models for mainstream discriminative tasks, i.e., unsupervised object discovery: saliency segmentation and object localization. However, the challenges exist as there is one structural difference between generative and discriminative models, which limits the direct use. Besides, the lack of explicitly la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09813","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/2303.09813/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":"2303.09813","created_at":"2026-07-05T05:52:11.051536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09813v1","created_at":"2026-07-05T05:52:11.051536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09813","created_at":"2026-07-05T05:52:11.051536+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7GM7PRF7CFC","created_at":"2026-07-05T05:52:11.051536+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7GM7PRF7CFCI57O","created_at":"2026-07-05T05:52:11.051536+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7GM7PRF","created_at":"2026-07-05T05:52:11.051536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22660","citing_title":"Prompting Diffusion Models for Zero-Shot Instance Segmentation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11683","citing_title":"Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23313","citing_title":"The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5","json":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5.json","graph_json":"https://pith.science/api/pith-number/B7GM7PRF7CFCI57OIXV4R6ZON5/graph.json","events_json":"https://pith.science/api/pith-number/B7GM7PRF7CFCI57OIXV4R6ZON5/events.json","paper":"https://pith.science/paper/B7GM7PRF"},"agent_actions":{"view_html":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5","download_json":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5.json","view_paper":"https://pith.science/paper/B7GM7PRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09813&json=true","fetch_graph":"https://pith.science/api/pith-number/B7GM7PRF7CFCI57OIXV4R6ZON5/graph.json","fetch_events":"https://pith.science/api/pith-number/B7GM7PRF7CFCI57OIXV4R6ZON5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5/action/storage_attestation","attest_author":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5/action/author_attestation","sign_citation":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5/action/citation_signature","submit_replication":"https://pith.science/pith/B7GM7PRF7CFCI57OIXV4R6ZON5/action/replication_record"}},"created_at":"2026-07-05T05:52:11.051536+00:00","updated_at":"2026-07-05T05:52:11.051536+00:00"}