{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2HWVY4JGT24Y33ICJNY7TSQQV5","short_pith_number":"pith:2HWVY4JG","schema_version":"1.0","canonical_sha256":"d1ed5c71269eb98ded024b71f9ca10af7da6aeb841715adf3ba699ba3eaecab0","source":{"kind":"arxiv","id":"1904.06487","version":5},"attestation_state":"computed","paper":{"title":"Semi-supervised Domain Adaptation via Minimax Entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Kate Saenko, Kuniaki Saito, Stan Sclaroff, Trevor Darrell","submitted_at":"2019-04-13T05:33:46Z","abstract_excerpt":"Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available in the target. To address this semi-supervised domain adaptation (SSDA) setting, we propose a novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model. Our base model consists of a feature encoding network, followed by a classification layer that computes the features' similarity to estimated prototypes (repr"},"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":"1904.06487","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-13T05:33:46Z","cross_cats_sorted":[],"title_canon_sha256":"b98cb9f9c96b1a5a54e5cdde24ee326b7a0ae1e131857a18182a591bc47c8274","abstract_canon_sha256":"1016586d6eea3267048d4622a1449376c64f24d2c9a2f52c7a63dde2e7a63df7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:41.187873Z","signature_b64":"rAjGwPz8Gnb0XiO8jIrwkXwWRzaqBmC7MZhVKWQJ/ZgfBIjeqEExQUhzK3fzexAbfb5UxPZCm/tHFDStlliUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1ed5c71269eb98ded024b71f9ca10af7da6aeb841715adf3ba699ba3eaecab0","last_reissued_at":"2026-07-05T00:04:41.187509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:41.187509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Domain Adaptation via Minimax Entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Kate Saenko, Kuniaki Saito, Stan Sclaroff, Trevor Darrell","submitted_at":"2019-04-13T05:33:46Z","abstract_excerpt":"Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available in the target. To address this semi-supervised domain adaptation (SSDA) setting, we propose a novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model. Our base model consists of a feature encoding network, followed by a classification layer that computes the features' similarity to estimated prototypes (repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06487","kind":"arxiv","version":5},"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/1904.06487/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":"1904.06487","created_at":"2026-07-05T00:04:41.187569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06487v5","created_at":"2026-07-05T00:04:41.187569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06487","created_at":"2026-07-05T00:04:41.187569+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HWVY4JGT24Y","created_at":"2026-07-05T00:04:41.187569+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HWVY4JGT24Y33IC","created_at":"2026-07-05T00:04:41.187569+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HWVY4JG","created_at":"2026-07-05T00:04:41.187569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.00781","citing_title":"Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5","json":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5.json","graph_json":"https://pith.science/api/pith-number/2HWVY4JGT24Y33ICJNY7TSQQV5/graph.json","events_json":"https://pith.science/api/pith-number/2HWVY4JGT24Y33ICJNY7TSQQV5/events.json","paper":"https://pith.science/paper/2HWVY4JG"},"agent_actions":{"view_html":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5","download_json":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5.json","view_paper":"https://pith.science/paper/2HWVY4JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06487&json=true","fetch_graph":"https://pith.science/api/pith-number/2HWVY4JGT24Y33ICJNY7TSQQV5/graph.json","fetch_events":"https://pith.science/api/pith-number/2HWVY4JGT24Y33ICJNY7TSQQV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5/action/storage_attestation","attest_author":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5/action/author_attestation","sign_citation":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5/action/citation_signature","submit_replication":"https://pith.science/pith/2HWVY4JGT24Y33ICJNY7TSQQV5/action/replication_record"}},"created_at":"2026-07-05T00:04:41.187569+00:00","updated_at":"2026-07-05T00:04:41.187569+00:00"}