{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5YE7LMALLU6ZE7XDPW7XD5TUJP","short_pith_number":"pith:5YE7LMAL","schema_version":"1.0","canonical_sha256":"ee09f5b00b5d3d927ee37dbf71f6744bf57103bdca3e6e14bd12fe7ecae23c71","source":{"kind":"arxiv","id":"2203.16427","version":1},"attestation_state":"computed","paper":{"title":"Balanced MSE for Imbalanced Visual Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cunjun Yu, Jiawei Ren, Mingyuan Zhang, Ziwei Liu","submitted_at":"2022-03-30T16:21:42Z","abstract_excerpt":"Data imbalance exists ubiquitously in real-world visual regressions, e.g., age estimation and pose estimation, hurting the model's generalizability and fairness. Thus, imbalanced regression gains increasing research attention recently. Compared to imbalanced classification, imbalanced regression focuses on continuous labels, which can be boundless and high-dimensional and hence more challenging. In this work, we identify that the widely used Mean Square Error (MSE) loss function can be ineffective in imbalanced regression. We revisit MSE from a statistical view and propose a novel loss functio"},"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":"2203.16427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T16:21:42Z","cross_cats_sorted":[],"title_canon_sha256":"fe0092b4a6f461cbc9651d8908ec1952a9cbea1e136f776937ea63786efed219","abstract_canon_sha256":"01e180e1e1b5ba0debb78e2331ece44c90370b5331425caa8bb6439660cc4043"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:10.561538Z","signature_b64":"suoAvMApOJUN/uw2jarAd7TfJ5Zo9Yeve2zb3mSV9kaj0WaK0uKUMILjcwquh6Kwj1eLOA6VowlGkElNqDp+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee09f5b00b5d3d927ee37dbf71f6744bf57103bdca3e6e14bd12fe7ecae23c71","last_reissued_at":"2026-07-05T04:10:10.561196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:10.561196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balanced MSE for Imbalanced Visual Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cunjun Yu, Jiawei Ren, Mingyuan Zhang, Ziwei Liu","submitted_at":"2022-03-30T16:21:42Z","abstract_excerpt":"Data imbalance exists ubiquitously in real-world visual regressions, e.g., age estimation and pose estimation, hurting the model's generalizability and fairness. Thus, imbalanced regression gains increasing research attention recently. Compared to imbalanced classification, imbalanced regression focuses on continuous labels, which can be boundless and high-dimensional and hence more challenging. In this work, we identify that the widely used Mean Square Error (MSE) loss function can be ineffective in imbalanced regression. We revisit MSE from a statistical view and propose a novel loss functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16427","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/2203.16427/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":"2203.16427","created_at":"2026-07-05T04:10:10.561255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16427v1","created_at":"2026-07-05T04:10:10.561255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16427","created_at":"2026-07-05T04:10:10.561255+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YE7LMALLU6Z","created_at":"2026-07-05T04:10:10.561255+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YE7LMALLU6ZE7XD","created_at":"2026-07-05T04:10:10.561255+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YE7LMAL","created_at":"2026-07-05T04:10:10.561255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04475","citing_title":"Advancing Marine Heatwave Forecasts: An Integrated Deep Learning Approach","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP","json":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP.json","graph_json":"https://pith.science/api/pith-number/5YE7LMALLU6ZE7XDPW7XD5TUJP/graph.json","events_json":"https://pith.science/api/pith-number/5YE7LMALLU6ZE7XDPW7XD5TUJP/events.json","paper":"https://pith.science/paper/5YE7LMAL"},"agent_actions":{"view_html":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP","download_json":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP.json","view_paper":"https://pith.science/paper/5YE7LMAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16427&json=true","fetch_graph":"https://pith.science/api/pith-number/5YE7LMALLU6ZE7XDPW7XD5TUJP/graph.json","fetch_events":"https://pith.science/api/pith-number/5YE7LMALLU6ZE7XDPW7XD5TUJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP/action/storage_attestation","attest_author":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP/action/author_attestation","sign_citation":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP/action/citation_signature","submit_replication":"https://pith.science/pith/5YE7LMALLU6ZE7XDPW7XD5TUJP/action/replication_record"}},"created_at":"2026-07-05T04:10:10.561255+00:00","updated_at":"2026-07-05T04:10:10.561255+00:00"}