{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TDQYST4P46XCHX3ZUG2FAZOUBH","short_pith_number":"pith:TDQYST4P","schema_version":"1.0","canonical_sha256":"98e1894f8fe7ae23df79a1b45065d409fc3ad80e6e1f0b55bbc8bded79d0e658","source":{"kind":"arxiv","id":"1904.01749","version":2},"attestation_state":"computed","paper":{"title":"Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dit-Yan Yeung, Lei Tai, Ming Liu, Ting Sun, Zhihan Gao","submitted_at":"2019-04-03T03:30:51Z","abstract_excerpt":"This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known defects of these cues are coarseness and incompleteness. We use super-pixel to refine them, and fuse the cues extracted from both a color image trained classifier and a gray image trained classifier to compensate for their incompleteness. The conditional random field is adapted to regulate the training process and to refine the outputs further. Besides initia"},"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":"1904.01749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-03T03:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"6c6f1607f55b29a0aba93c502b8b0a4d250197d3b45e35161d10b0a37bf2943a","abstract_canon_sha256":"ce7c794cedb20b51c2fceba62cf2a10c34afbc1116433dc504d1004bcfefb65e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:23.064523Z","signature_b64":"fUsDJCahIy0tw8AytlUTFW7Uz1m0DLDIarqRNR+ngGGfImUBG3Rtfm1ls7JOO8FPUjtdU5H5ebBoIlSjkH6KBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98e1894f8fe7ae23df79a1b45065d409fc3ad80e6e1f0b55bbc8bded79d0e658","last_reissued_at":"2026-05-17T23:43:23.063897Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:23.063897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dit-Yan Yeung, Lei Tai, Ming Liu, Ting Sun, Zhihan Gao","submitted_at":"2019-04-03T03:30:51Z","abstract_excerpt":"This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known defects of these cues are coarseness and incompleteness. We use super-pixel to refine them, and fuse the cues extracted from both a color image trained classifier and a gray image trained classifier to compensate for their incompleteness. The conditional random field is adapted to regulate the training process and to refine the outputs further. Besides initia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01749","kind":"arxiv","version":2},"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":"1904.01749","created_at":"2026-05-17T23:43:23.063990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01749v2","created_at":"2026-05-17T23:43:23.063990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01749","created_at":"2026-05-17T23:43:23.063990+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDQYST4P46XC","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDQYST4P46XCHX3Z","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDQYST4P","created_at":"2026-05-18T12:33:27.125529+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/TDQYST4P46XCHX3ZUG2FAZOUBH","json":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH.json","graph_json":"https://pith.science/api/pith-number/TDQYST4P46XCHX3ZUG2FAZOUBH/graph.json","events_json":"https://pith.science/api/pith-number/TDQYST4P46XCHX3ZUG2FAZOUBH/events.json","paper":"https://pith.science/paper/TDQYST4P"},"agent_actions":{"view_html":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH","download_json":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH.json","view_paper":"https://pith.science/paper/TDQYST4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01749&json=true","fetch_graph":"https://pith.science/api/pith-number/TDQYST4P46XCHX3ZUG2FAZOUBH/graph.json","fetch_events":"https://pith.science/api/pith-number/TDQYST4P46XCHX3ZUG2FAZOUBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH/action/storage_attestation","attest_author":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH/action/author_attestation","sign_citation":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH/action/citation_signature","submit_replication":"https://pith.science/pith/TDQYST4P46XCHX3ZUG2FAZOUBH/action/replication_record"}},"created_at":"2026-05-17T23:43:23.063990+00:00","updated_at":"2026-05-17T23:43:23.063990+00:00"}