{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LERAY4VVWCE7MFOGAAUEYVHEXI","short_pith_number":"pith:LERAY4VV","schema_version":"1.0","canonical_sha256":"59220c72b5b089f615c600284c54e4ba19c73f2818736c85556872e0851fdcd4","source":{"kind":"arxiv","id":"1808.01625","version":3},"attestation_state":"computed","paper":{"title":"Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Mayer, Gr\\'egory Paul, Radu Timofte","submitted_at":"2018-08-05T14:19:19Z","abstract_excerpt":"Generating training sets for deep convolutional neural networks (DCNNs) is a bottleneck for modern real-world applications. This is a demanding task for applications where annotating training data is costly, such as in semantic segmentation. In the literature, there is still a gap between the performance achieved by a network trained on full and on weak annotations. In this paper, we establish a strategy to measure this gap and to identify the ingredients necessary to reduce it.\n  On scribbles, we establish new state-of-the-art results: we obtain a mIoU of 75.6% without, and 75.7% with CRF pos"},"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":"1808.01625","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-05T14:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"c58d8bd8a0f4b4d90900cb2024a44263954b946354a87c807fab5b6f9e54ae84","abstract_canon_sha256":"812399c1f1af1fb8ee9957482516cb13f2686caa6d83fddd9bcda642daa6ce36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:30.592632Z","signature_b64":"qBw6gLGzAEUecg1Li1cKTbIGbD8rl+BhQKwwk9rxpAdk8n1SZ9EqzJj98Q02angwBa3neWQ6MccQjJ1Kqtq9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59220c72b5b089f615c600284c54e4ba19c73f2818736c85556872e0851fdcd4","last_reissued_at":"2026-05-17T23:47:30.592154Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:30.592154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Mayer, Gr\\'egory Paul, Radu Timofte","submitted_at":"2018-08-05T14:19:19Z","abstract_excerpt":"Generating training sets for deep convolutional neural networks (DCNNs) is a bottleneck for modern real-world applications. This is a demanding task for applications where annotating training data is costly, such as in semantic segmentation. In the literature, there is still a gap between the performance achieved by a network trained on full and on weak annotations. In this paper, we establish a strategy to measure this gap and to identify the ingredients necessary to reduce it.\n  On scribbles, we establish new state-of-the-art results: we obtain a mIoU of 75.6% without, and 75.7% with CRF pos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01625","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":"1808.01625","created_at":"2026-05-17T23:47:30.592218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01625v3","created_at":"2026-05-17T23:47:30.592218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01625","created_at":"2026-05-17T23:47:30.592218+00:00"},{"alias_kind":"pith_short_12","alias_value":"LERAY4VVWCE7","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LERAY4VVWCE7MFOG","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LERAY4VV","created_at":"2026-05-18T12:32:37.024351+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/LERAY4VVWCE7MFOGAAUEYVHEXI","json":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI.json","graph_json":"https://pith.science/api/pith-number/LERAY4VVWCE7MFOGAAUEYVHEXI/graph.json","events_json":"https://pith.science/api/pith-number/LERAY4VVWCE7MFOGAAUEYVHEXI/events.json","paper":"https://pith.science/paper/LERAY4VV"},"agent_actions":{"view_html":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI","download_json":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI.json","view_paper":"https://pith.science/paper/LERAY4VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01625&json=true","fetch_graph":"https://pith.science/api/pith-number/LERAY4VVWCE7MFOGAAUEYVHEXI/graph.json","fetch_events":"https://pith.science/api/pith-number/LERAY4VVWCE7MFOGAAUEYVHEXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI/action/storage_attestation","attest_author":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI/action/author_attestation","sign_citation":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI/action/citation_signature","submit_replication":"https://pith.science/pith/LERAY4VVWCE7MFOGAAUEYVHEXI/action/replication_record"}},"created_at":"2026-05-17T23:47:30.592218+00:00","updated_at":"2026-05-17T23:47:30.592218+00:00"}