{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R77XM6ZKVTSX6TCXSYZ6QPTAZ2","short_pith_number":"pith:R77XM6ZK","schema_version":"1.0","canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","source":{"kind":"arxiv","id":"1807.04629","version":4},"attestation_state":"computed","paper":{"title":"Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Hanwei Wu, Markus Flierl","submitted_at":"2018-07-12T15:08:31Z","abstract_excerpt":"Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation learning for downstream tasks, such as image retrieval. We first describe the VQ-VAE in the context of an information-theoretic framework. We show that the regularization term on the learned representation is determined by the size of the embedded codebook before the training and it affects the generalization ability of the model. As a result, we introduce a hyper"},"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":"1807.04629","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-07-12T15:08:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"83425a6b1886883b0951b3063b4e4c93937b582cd2e73c9c938d911ee2bad889","abstract_canon_sha256":"c21ead5e2d8b0caecd7a1aabcafa0e172e0610a8371e73bb70f42e3e572500e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:15.911443Z","signature_b64":"EaA9OoR3kzhfub7SSq9nsXMYN/WfXoQwqNuhiWa1hcNKSxiuXsNeePKN2YGxxP2s57+nWlJr45om4feKtQT1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","last_reissued_at":"2026-05-17T23:52:15.910642Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:15.910642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Hanwei Wu, Markus Flierl","submitted_at":"2018-07-12T15:08:31Z","abstract_excerpt":"Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation learning for downstream tasks, such as image retrieval. We first describe the VQ-VAE in the context of an information-theoretic framework. We show that the regularization term on the learned representation is determined by the size of the embedded codebook before the training and it affects the generalization ability of the model. As a result, we introduce a hyper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04629","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":""},"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":"1807.04629","created_at":"2026-05-17T23:52:15.910786+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04629v4","created_at":"2026-05-17T23:52:15.910786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04629","created_at":"2026-05-17T23:52:15.910786+00:00"},{"alias_kind":"pith_short_12","alias_value":"R77XM6ZKVTSX","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R77XM6ZKVTSX6TCX","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R77XM6ZK","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20040","citing_title":"Cross-Layer Discrete Concept Discovery for Interpreting Language Models","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2","json":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2.json","graph_json":"https://pith.science/api/pith-number/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/graph.json","events_json":"https://pith.science/api/pith-number/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/events.json","paper":"https://pith.science/paper/R77XM6ZK"},"agent_actions":{"view_html":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2","download_json":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2.json","view_paper":"https://pith.science/paper/R77XM6ZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04629&json=true","fetch_graph":"https://pith.science/api/pith-number/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/action/storage_attestation","attest_author":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/action/author_attestation","sign_citation":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/action/citation_signature","submit_replication":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/action/replication_record"}},"created_at":"2026-05-17T23:52:15.910786+00:00","updated_at":"2026-05-17T23:52:15.910786+00:00"}