{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YPUG7CL5XESHSZPUMNEQJISFSJ","short_pith_number":"pith:YPUG7CL5","schema_version":"1.0","canonical_sha256":"c3e86f897db9247965f4634904a245927a07e2e8443501af8f4ee3b4d8582b9c","source":{"kind":"arxiv","id":"2105.15203","version":3},"attestation_state":"computed","paper":{"title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Enze Xie, Jose M. Alvarez, Ping Luo, Wenhai Wang, Zhiding Yu","submitted_at":"2021-05-31T17:59:51Z","abstract_excerpt":"We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a novel hierarchically structured Transformer encoder which outputs multiscale features. It does not need positional encoding, thereby avoiding the interpolation of positional codes which leads to decreased performance when the testing resolution differs from training. 2) SegFormer avoids complex decoders. The proposed MLP decoder aggregates information from different"},"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":"2105.15203","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-31T17:59:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60c34f164d563982a7a00fa7faee2187232ea7b6aeff84e39050622b8bc9fce9","abstract_canon_sha256":"2b1ee0ec59b6fb55afa413e3281e5b46489abf3d3ecd8c89bd50786be779574a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:41.703252Z","signature_b64":"XIFP+EYaDuSaIuWmVLZn65jOxCnaRfJcVU1YCiYs0Pfmoms550eA1Wd3Jpz2miLLtpKPjtgxwXZ1D1xClAhGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e86f897db9247965f4634904a245927a07e2e8443501af8f4ee3b4d8582b9c","last_reissued_at":"2026-07-05T03:26:41.702672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:41.702672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Enze Xie, Jose M. Alvarez, Ping Luo, Wenhai Wang, Zhiding Yu","submitted_at":"2021-05-31T17:59:51Z","abstract_excerpt":"We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a novel hierarchically structured Transformer encoder which outputs multiscale features. It does not need positional encoding, thereby avoiding the interpolation of positional codes which leads to decreased performance when the testing resolution differs from training. 2) SegFormer avoids complex decoders. The proposed MLP decoder aggregates information from different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.15203","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/2105.15203/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":"2105.15203","created_at":"2026-07-05T03:26:41.702735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.15203v3","created_at":"2026-07-05T03:26:41.702735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.15203","created_at":"2026-07-05T03:26:41.702735+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPUG7CL5XESH","created_at":"2026-07-05T03:26:41.702735+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPUG7CL5XESHSZPU","created_at":"2026-07-05T03:26:41.702735+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPUG7CL5","created_at":"2026-07-05T03:26:41.702735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09162","citing_title":"Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08517","citing_title":"A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02370","citing_title":"A Simulation Platform for Flapping-Wing Vehicles","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23747","citing_title":"Revitalizing Dense Material Segmentation: Stabilized Vision Transformers and the Generalization Paradox","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":284,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27958","citing_title":"TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06311","citing_title":"Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22507","citing_title":"Railway Artificial Intelligence Learning Benchmark (RAIL-BENCH): A Benchmark Suite for Perception in the Railway Domain","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12622","citing_title":"Efficient Semantic Image Communication for Traffic Monitoring at the Edge","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06113","citing_title":"SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14805","citing_title":"From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ","json":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ.json","graph_json":"https://pith.science/api/pith-number/YPUG7CL5XESHSZPUMNEQJISFSJ/graph.json","events_json":"https://pith.science/api/pith-number/YPUG7CL5XESHSZPUMNEQJISFSJ/events.json","paper":"https://pith.science/paper/YPUG7CL5"},"agent_actions":{"view_html":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ","download_json":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ.json","view_paper":"https://pith.science/paper/YPUG7CL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.15203&json=true","fetch_graph":"https://pith.science/api/pith-number/YPUG7CL5XESHSZPUMNEQJISFSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YPUG7CL5XESHSZPUMNEQJISFSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ/action/storage_attestation","attest_author":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ/action/author_attestation","sign_citation":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ/action/citation_signature","submit_replication":"https://pith.science/pith/YPUG7CL5XESHSZPUMNEQJISFSJ/action/replication_record"}},"created_at":"2026-07-05T03:26:41.702735+00:00","updated_at":"2026-07-05T03:26:41.702735+00:00"}