{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JO5AOGGGZ4H43L43YQGKNFMHE5","short_pith_number":"pith:JO5AOGGG","schema_version":"1.0","canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","source":{"kind":"arxiv","id":"1807.09200","version":1},"attestation_state":"computed","paper":{"title":"Self-Paced Learning with Adaptive Deep Visual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Vithursan Thangarasa","submitted_at":"2018-07-24T16:01:00Z","abstract_excerpt":"Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performance. In this paper, we introduce Self-Paced Learning with Adaptive Deep Visual Embeddings (SPL-ADVisE), a novel end-to-end training protocol that unites self-paced learning (SPL) and deep metric learning (DML). We leverage the Magnet Loss to train an embedding convolutional neural "},"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":"1807.09200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T16:01:00Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b72bd5034e9585e95d91557de291820f67265d28ee778c48bd1fe4cedbf7f667","abstract_canon_sha256":"e2d465f509dde79805a482f087c0f8c504730be6828a76e32c2be5430670cda6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:56.441069Z","signature_b64":"NHCcUJzjB1/kail0yk/7ko4VBArGvpfgGqkbZV6gBMGAn601sQjhYcnTNbWJyVsHci52O/45Ntlw9jYuWN2CDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bba0718c6cf0fcdaf9bc40ca695872773fa96134d7604f7eb778dc816f88453","last_reissued_at":"2026-05-18T00:09:56.440403Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:56.440403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Paced Learning with Adaptive Deep Visual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Vithursan Thangarasa","submitted_at":"2018-07-24T16:01:00Z","abstract_excerpt":"Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performance. In this paper, we introduce Self-Paced Learning with Adaptive Deep Visual Embeddings (SPL-ADVisE), a novel end-to-end training protocol that unites self-paced learning (SPL) and deep metric learning (DML). We leverage the Magnet Loss to train an embedding convolutional neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09200","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":""},"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":"1807.09200","created_at":"2026-05-18T00:09:56.440500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09200v1","created_at":"2026-05-18T00:09:56.440500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09200","created_at":"2026-05-18T00:09:56.440500+00:00"},{"alias_kind":"pith_short_12","alias_value":"JO5AOGGGZ4H4","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JO5AOGGGZ4H43L43","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JO5AOGGG","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08771","citing_title":"Submodular Batch Selection for Training Deep Neural Networks","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5","json":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5.json","graph_json":"https://pith.science/api/pith-number/JO5AOGGGZ4H43L43YQGKNFMHE5/graph.json","events_json":"https://pith.science/api/pith-number/JO5AOGGGZ4H43L43YQGKNFMHE5/events.json","paper":"https://pith.science/paper/JO5AOGGG"},"agent_actions":{"view_html":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5","download_json":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5.json","view_paper":"https://pith.science/paper/JO5AOGGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09200&json=true","fetch_graph":"https://pith.science/api/pith-number/JO5AOGGGZ4H43L43YQGKNFMHE5/graph.json","fetch_events":"https://pith.science/api/pith-number/JO5AOGGGZ4H43L43YQGKNFMHE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/action/storage_attestation","attest_author":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/action/author_attestation","sign_citation":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/action/citation_signature","submit_replication":"https://pith.science/pith/JO5AOGGGZ4H43L43YQGKNFMHE5/action/replication_record"}},"created_at":"2026-05-18T00:09:56.440500+00:00","updated_at":"2026-05-18T00:09:56.440500+00:00"}