{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WV6MKUHCPZ2JNEDBT5FS5YTL75","short_pith_number":"pith:WV6MKUHC","schema_version":"1.0","canonical_sha256":"b57cc550e27e749690619f4b2ee26bff55771e9988a56d9bef04743a028f4353","source":{"kind":"arxiv","id":"2407.07441","version":2},"attestation_state":"computed","paper":{"title":"HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangwei Gao, Guoan Xu, Ligeng Chen, Tao Wu, Wenjing Jia","submitted_at":"2024-07-10T07:53:24Z","abstract_excerpt":"Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions. However, there is still room for enhancement, particularly when considering constraints on computational resources. In this paper, we introduce HAFormer, a model that combines the hierarchical features extraction ability of CNNs with the global dependency modeling capability of Transformers to tackle lightweight semantic segmentation challenges. Specifically, we"},"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":"2407.07441","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T07:53:24Z","cross_cats_sorted":[],"title_canon_sha256":"9a47e4c67c45211135fcedefa793dbfff2ce449e9c7bfdc83a0499c822d64f2d","abstract_canon_sha256":"d6c6f73dbcaf58d8ca00e0a021c5fa0aed5851139a2abbd2dd7b3a3eea8277a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:39.245022Z","signature_b64":"K8w1+QjExIltHq9EdRB3iengYWuii/t49ke3DJfNn3AYfsR48eRA9ofhG0r3mWPSIOLN3lWc4qvzq91Y3lasCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b57cc550e27e749690619f4b2ee26bff55771e9988a56d9bef04743a028f4353","last_reissued_at":"2026-07-05T08:42:39.244616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:39.244616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangwei Gao, Guoan Xu, Ligeng Chen, Tao Wu, Wenjing Jia","submitted_at":"2024-07-10T07:53:24Z","abstract_excerpt":"Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions. However, there is still room for enhancement, particularly when considering constraints on computational resources. In this paper, we introduce HAFormer, a model that combines the hierarchical features extraction ability of CNNs with the global dependency modeling capability of Transformers to tackle lightweight semantic segmentation challenges. Specifically, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07441","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.07441/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":"2407.07441","created_at":"2026-07-05T08:42:39.244671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07441v2","created_at":"2026-07-05T08:42:39.244671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07441","created_at":"2026-07-05T08:42:39.244671+00:00"},{"alias_kind":"pith_short_12","alias_value":"WV6MKUHCPZ2J","created_at":"2026-07-05T08:42:39.244671+00:00"},{"alias_kind":"pith_short_16","alias_value":"WV6MKUHCPZ2JNEDB","created_at":"2026-07-05T08:42:39.244671+00:00"},{"alias_kind":"pith_short_8","alias_value":"WV6MKUHC","created_at":"2026-07-05T08:42:39.244671+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/WV6MKUHCPZ2JNEDBT5FS5YTL75","json":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75.json","graph_json":"https://pith.science/api/pith-number/WV6MKUHCPZ2JNEDBT5FS5YTL75/graph.json","events_json":"https://pith.science/api/pith-number/WV6MKUHCPZ2JNEDBT5FS5YTL75/events.json","paper":"https://pith.science/paper/WV6MKUHC"},"agent_actions":{"view_html":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75","download_json":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75.json","view_paper":"https://pith.science/paper/WV6MKUHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07441&json=true","fetch_graph":"https://pith.science/api/pith-number/WV6MKUHCPZ2JNEDBT5FS5YTL75/graph.json","fetch_events":"https://pith.science/api/pith-number/WV6MKUHCPZ2JNEDBT5FS5YTL75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75/action/storage_attestation","attest_author":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75/action/author_attestation","sign_citation":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75/action/citation_signature","submit_replication":"https://pith.science/pith/WV6MKUHCPZ2JNEDBT5FS5YTL75/action/replication_record"}},"created_at":"2026-07-05T08:42:39.244671+00:00","updated_at":"2026-07-05T08:42:39.244671+00:00"}