{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7OLMTF4DW2BJQCFJHW2R4VCZTV","short_pith_number":"pith:7OLMTF4D","schema_version":"1.0","canonical_sha256":"fb96c99783b6829808a93db51e54599d6303ffa0c2323100118b195c73efc225","source":{"kind":"arxiv","id":"1712.00661","version":3},"attestation_state":"computed","paper":{"title":"Mix-and-Match Tuning for Self-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Ping Luo, Xiaohang Zhan, Xiaoou Tang, Ziwei Liu","submitted_at":"2017-12-02T20:25:37Z","abstract_excerpt":"Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g. ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently proposed to pre-train a network without any human-provided labels. The key of this new form of learning is to design a proxy task (e.g. image colorization), from which a discriminative loss can be formulated on unlabeled data. Many proxy tasks, however, lack the critical supervision signals that could induce discriminative representation for the target image se"},"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":"1712.00661","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-02T20:25:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c62fcdc6f19b008dbe35c4ea615fcda621918e6f24a95d4716b9972898338c12","abstract_canon_sha256":"f604d79da849847c0fdb89352d7e0d395880e99feca754f58ac45a592bd8f747"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:54.274651Z","signature_b64":"9A6XD9OdvLzwQPTwhe+GHvDlW6hJl2HMOsucJXvthCvz6o26Sfly/BIfo2lD3r0cqlWd4MpQCtPEhZmGOwUeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb96c99783b6829808a93db51e54599d6303ffa0c2323100118b195c73efc225","last_reissued_at":"2026-05-18T00:24:54.273878Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:54.273878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mix-and-Match Tuning for Self-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Ping Luo, Xiaohang Zhan, Xiaoou Tang, Ziwei Liu","submitted_at":"2017-12-02T20:25:37Z","abstract_excerpt":"Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g. ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently proposed to pre-train a network without any human-provided labels. The key of this new form of learning is to design a proxy task (e.g. image colorization), from which a discriminative loss can be formulated on unlabeled data. Many proxy tasks, however, lack the critical supervision signals that could induce discriminative representation for the target image se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00661","kind":"arxiv","version":3},"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":"1712.00661","created_at":"2026-05-18T00:24:54.274020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00661v3","created_at":"2026-05-18T00:24:54.274020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00661","created_at":"2026-05-18T00:24:54.274020+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OLMTF4DW2BJ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OLMTF4DW2BJQCFJ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OLMTF4D","created_at":"2026-05-18T12:31:05.417338+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/7OLMTF4DW2BJQCFJHW2R4VCZTV","json":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV.json","graph_json":"https://pith.science/api/pith-number/7OLMTF4DW2BJQCFJHW2R4VCZTV/graph.json","events_json":"https://pith.science/api/pith-number/7OLMTF4DW2BJQCFJHW2R4VCZTV/events.json","paper":"https://pith.science/paper/7OLMTF4D"},"agent_actions":{"view_html":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV","download_json":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV.json","view_paper":"https://pith.science/paper/7OLMTF4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00661&json=true","fetch_graph":"https://pith.science/api/pith-number/7OLMTF4DW2BJQCFJHW2R4VCZTV/graph.json","fetch_events":"https://pith.science/api/pith-number/7OLMTF4DW2BJQCFJHW2R4VCZTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV/action/storage_attestation","attest_author":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV/action/author_attestation","sign_citation":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV/action/citation_signature","submit_replication":"https://pith.science/pith/7OLMTF4DW2BJQCFJHW2R4VCZTV/action/replication_record"}},"created_at":"2026-05-18T00:24:54.274020+00:00","updated_at":"2026-05-18T00:24:54.274020+00:00"}