{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LSHQPQ4ZI5OF2O3ZZSPR7OADXV","short_pith_number":"pith:LSHQPQ4Z","schema_version":"1.0","canonical_sha256":"5c8f07c399475c5d3b79cc9f1fb803bd7a7a35f93746f6097567a470fb367cb3","source":{"kind":"arxiv","id":"2412.11076","version":3},"attestation_state":"computed","paper":{"title":"MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kexue Fu, Shuo Wang, Yucong Meng, Zhijian Song, Zhiwei Yang","submitted_at":"2024-12-15T06:20:41Z","abstract_excerpt":"Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the poten"},"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":"2412.11076","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T06:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"cde2c42bc3a1e552bcdb12c157f51eb683e0766035e3e3dded4ead2b9a91a9fb","abstract_canon_sha256":"c990b697842b932209eb7a0feb52cfd99f69fcfa5d73ded9766f2f0f127ddce5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:08.635719Z","signature_b64":"o7tx4iR23URrupm27WJvqHxDIyc5kEk1gyPk7wzqzeRxpw9kPafiCFz7hkou5TxbKBmMhe55+6c8Sks37bQ5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c8f07c399475c5d3b79cc9f1fb803bd7a7a35f93746f6097567a470fb367cb3","last_reissued_at":"2026-07-05T10:02:08.635251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:08.635251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kexue Fu, Shuo Wang, Yucong Meng, Zhijian Song, Zhiwei Yang","submitted_at":"2024-12-15T06:20:41Z","abstract_excerpt":"Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the poten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11076","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.11076/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":"2412.11076","created_at":"2026-07-05T10:02:08.635308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11076v3","created_at":"2026-07-05T10:02:08.635308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11076","created_at":"2026-07-05T10:02:08.635308+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSHQPQ4ZI5OF","created_at":"2026-07-05T10:02:08.635308+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSHQPQ4ZI5OF2O3Z","created_at":"2026-07-05T10:02:08.635308+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSHQPQ4Z","created_at":"2026-07-05T10:02:08.635308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":250,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":280,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04593","citing_title":"DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV","json":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV.json","graph_json":"https://pith.science/api/pith-number/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/graph.json","events_json":"https://pith.science/api/pith-number/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/events.json","paper":"https://pith.science/paper/LSHQPQ4Z"},"agent_actions":{"view_html":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV","download_json":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV.json","view_paper":"https://pith.science/paper/LSHQPQ4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11076&json=true","fetch_graph":"https://pith.science/api/pith-number/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/graph.json","fetch_events":"https://pith.science/api/pith-number/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/action/storage_attestation","attest_author":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/action/author_attestation","sign_citation":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/action/citation_signature","submit_replication":"https://pith.science/pith/LSHQPQ4ZI5OF2O3ZZSPR7OADXV/action/replication_record"}},"created_at":"2026-07-05T10:02:08.635308+00:00","updated_at":"2026-07-05T10:02:08.635308+00:00"}