{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JP3JVVVEJH5ZRJJS6AFHHLHXT5","short_pith_number":"pith:JP3JVVVE","schema_version":"1.0","canonical_sha256":"4bf69ad6a449fb98a532f00a73acf79f6e8b91d9a0ea7513242d0d8e37644a9c","source":{"kind":"arxiv","id":"2406.01203","version":1},"attestation_state":"computed","paper":{"title":"Scaling Up Deep Clustering Methods Beyond ImageNet-1K","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Diana Petrusheva, Felix Michels, Kaspar Senft, Markus Kollmann, Nikolas Adaloglou","submitted_at":"2024-06-03T11:13:27Z","abstract_excerpt":"Deep image clustering methods are typically evaluated on small-scale balanced classification datasets while feature-based $k$-means has been applied on proprietary billion-scale datasets. In this work, we explore the performance of feature-based deep clustering approaches on large-scale benchmarks whilst disentangling the impact of the following data-related factors: i) class imbalance, ii) class granularity, iii) easy-to-recognize classes, and iv) the ability to capture multiple classes. Consequently, we develop multiple new benchmarks based on ImageNet21K. Our experimental analysis reveals t"},"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":"2406.01203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T11:13:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"63ea726027d690d241d3bf5e69d1613c7116bd544c8c45bd83174039e8532f7f","abstract_canon_sha256":"6d928b8d577882b6ac49cdb40f01b17761d327b5f426b65408327427d3816e86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:36.828186Z","signature_b64":"QE/GtHoadRypsDAvUQ7wYzlIcEtOJk5Xntcf0w5IEtytAYBIVOiAjlI/sD21FPmigmq7utRk4myw5a/Y2tSiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf69ad6a449fb98a532f00a73acf79f6e8b91d9a0ea7513242d0d8e37644a9c","last_reissued_at":"2026-07-05T08:26:36.827674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:36.827674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Up Deep Clustering Methods Beyond ImageNet-1K","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Diana Petrusheva, Felix Michels, Kaspar Senft, Markus Kollmann, Nikolas Adaloglou","submitted_at":"2024-06-03T11:13:27Z","abstract_excerpt":"Deep image clustering methods are typically evaluated on small-scale balanced classification datasets while feature-based $k$-means has been applied on proprietary billion-scale datasets. In this work, we explore the performance of feature-based deep clustering approaches on large-scale benchmarks whilst disentangling the impact of the following data-related factors: i) class imbalance, ii) class granularity, iii) easy-to-recognize classes, and iv) the ability to capture multiple classes. Consequently, we develop multiple new benchmarks based on ImageNet21K. Our experimental analysis reveals t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01203","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/2406.01203/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":"2406.01203","created_at":"2026-07-05T08:26:36.827741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01203v1","created_at":"2026-07-05T08:26:36.827741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01203","created_at":"2026-07-05T08:26:36.827741+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP3JVVVEJH5Z","created_at":"2026-07-05T08:26:36.827741+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP3JVVVEJH5ZRJJS","created_at":"2026-07-05T08:26:36.827741+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP3JVVVE","created_at":"2026-07-05T08:26:36.827741+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/JP3JVVVEJH5ZRJJS6AFHHLHXT5","json":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5.json","graph_json":"https://pith.science/api/pith-number/JP3JVVVEJH5ZRJJS6AFHHLHXT5/graph.json","events_json":"https://pith.science/api/pith-number/JP3JVVVEJH5ZRJJS6AFHHLHXT5/events.json","paper":"https://pith.science/paper/JP3JVVVE"},"agent_actions":{"view_html":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5","download_json":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5.json","view_paper":"https://pith.science/paper/JP3JVVVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01203&json=true","fetch_graph":"https://pith.science/api/pith-number/JP3JVVVEJH5ZRJJS6AFHHLHXT5/graph.json","fetch_events":"https://pith.science/api/pith-number/JP3JVVVEJH5ZRJJS6AFHHLHXT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5/action/storage_attestation","attest_author":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5/action/author_attestation","sign_citation":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5/action/citation_signature","submit_replication":"https://pith.science/pith/JP3JVVVEJH5ZRJJS6AFHHLHXT5/action/replication_record"}},"created_at":"2026-07-05T08:26:36.827741+00:00","updated_at":"2026-07-05T08:26:36.827741+00:00"}