{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JCEXIYDGKDAFMGETI6455SCVPT","short_pith_number":"pith:JCEXIYDG","schema_version":"1.0","canonical_sha256":"488974606650c056189347b9dec8557cf6be5fc2ebf6faeb28a3057fb493556b","source":{"kind":"arxiv","id":"2204.05525","version":1},"attestation_state":"computed","paper":{"title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Gang Yu, Guozhong Luo, Tao Chen, Wenqiang Zhang, Wenyu Liu, Xinggang Wang, Zilong Huang","submitted_at":"2022-04-12T04:51:42Z","abstract_excerpt":"Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named \\textbf{To}ken \\textbf{P}yramid Vision Trans\\textbf{former} (\\textbf{TopFormer}). The proposed \\textbf{TopFormer} takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that o"},"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":"2204.05525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-12T04:51:42Z","cross_cats_sorted":[],"title_canon_sha256":"5a14e470a2609dc1dbbe757dc35e1afa5a34c7d0cdc81bb379807c707e491f56","abstract_canon_sha256":"2562d475f3d0bb47213ca22c3208b98592034a7c53248a1a0fe41fea145aa130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:58.844359Z","signature_b64":"SZ0NRQxDkLW/U9kXPlkv22L9D92mP/GS/1p0PS1izyKcFRnH1wXVwc/B8KFDSOSHt5JWDT69DoAMWatVNuRyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488974606650c056189347b9dec8557cf6be5fc2ebf6faeb28a3057fb493556b","last_reissued_at":"2026-07-05T04:13:58.843959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:58.843959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Gang Yu, Guozhong Luo, Tao Chen, Wenqiang Zhang, Wenyu Liu, Xinggang Wang, Zilong Huang","submitted_at":"2022-04-12T04:51:42Z","abstract_excerpt":"Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named \\textbf{To}ken \\textbf{P}yramid Vision Trans\\textbf{former} (\\textbf{TopFormer}). The proposed \\textbf{TopFormer} takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05525","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/2204.05525/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":"2204.05525","created_at":"2026-07-05T04:13:58.844016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05525v1","created_at":"2026-07-05T04:13:58.844016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05525","created_at":"2026-07-05T04:13:58.844016+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCEXIYDGKDAF","created_at":"2026-07-05T04:13:58.844016+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCEXIYDGKDAFMGET","created_at":"2026-07-05T04:13:58.844016+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCEXIYDG","created_at":"2026-07-05T04:13:58.844016+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/JCEXIYDGKDAFMGETI6455SCVPT","json":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT.json","graph_json":"https://pith.science/api/pith-number/JCEXIYDGKDAFMGETI6455SCVPT/graph.json","events_json":"https://pith.science/api/pith-number/JCEXIYDGKDAFMGETI6455SCVPT/events.json","paper":"https://pith.science/paper/JCEXIYDG"},"agent_actions":{"view_html":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT","download_json":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT.json","view_paper":"https://pith.science/paper/JCEXIYDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05525&json=true","fetch_graph":"https://pith.science/api/pith-number/JCEXIYDGKDAFMGETI6455SCVPT/graph.json","fetch_events":"https://pith.science/api/pith-number/JCEXIYDGKDAFMGETI6455SCVPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT/action/storage_attestation","attest_author":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT/action/author_attestation","sign_citation":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT/action/citation_signature","submit_replication":"https://pith.science/pith/JCEXIYDGKDAFMGETI6455SCVPT/action/replication_record"}},"created_at":"2026-07-05T04:13:58.844016+00:00","updated_at":"2026-07-05T04:13:58.844016+00:00"}