{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5365GYKYAVK3ZUBWNTTEPSXEWN","short_pith_number":"pith:5365GYKY","schema_version":"1.0","canonical_sha256":"eefdd361580555bcd0366ce647cae4b370504f9fd37ed7565862da890780ee67","source":{"kind":"arxiv","id":"2403.05061","version":3},"attestation_state":"computed","paper":{"title":"RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsuk Kum, Geonho Bang, Jisong Kim, Jun Won Choi, Kwangjin Choi","submitted_at":"2024-03-08T05:15:48Z","abstract_excerpt":"The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve the representation of radar data by leveraging LiDAR data. RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components: Cross-Modality Alignment (CMA), Activation-based Feature Distillation (AFD), and Proposal-based Feature Distillation (PFD). CMA enhances the density of radar features by emp"},"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":"2403.05061","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T05:15:48Z","cross_cats_sorted":[],"title_canon_sha256":"489ab80daf88d63c3d675cd3b94ab3eb23dc63f6da4d191243071d5f8ede0540","abstract_canon_sha256":"8dbaa6d06abffeb408196ace410da4555585172765a735d2afa94fea27063982"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:10.944509Z","signature_b64":"oesBZa/4vwpm+lhpQmBfPMur5S4sj2R70aOihecx4lJkSSJaZrvqdXkfClvUNiqxlpla6ncjniMsjtd5YPB7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eefdd361580555bcd0366ce647cae4b370504f9fd37ed7565862da890780ee67","last_reissued_at":"2026-07-05T10:20:10.943997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:10.943997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsuk Kum, Geonho Bang, Jisong Kim, Jun Won Choi, Kwangjin Choi","submitted_at":"2024-03-08T05:15:48Z","abstract_excerpt":"The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve the representation of radar data by leveraging LiDAR data. RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components: Cross-Modality Alignment (CMA), Activation-based Feature Distillation (AFD), and Proposal-based Feature Distillation (PFD). CMA enhances the density of radar features by emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05061","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/2403.05061/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":"2403.05061","created_at":"2026-07-05T10:20:10.944057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05061v3","created_at":"2026-07-05T10:20:10.944057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05061","created_at":"2026-07-05T10:20:10.944057+00:00"},{"alias_kind":"pith_short_12","alias_value":"5365GYKYAVK3","created_at":"2026-07-05T10:20:10.944057+00:00"},{"alias_kind":"pith_short_16","alias_value":"5365GYKYAVK3ZUBW","created_at":"2026-07-05T10:20:10.944057+00:00"},{"alias_kind":"pith_short_8","alias_value":"5365GYKY","created_at":"2026-07-05T10:20:10.944057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.04950","citing_title":"MORDA: A Synthetic Dataset to Facilitate Adaptation of Object Detectors to Unseen Real-target Domain While Preserving Performance on Real-source Domain","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN","json":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN.json","graph_json":"https://pith.science/api/pith-number/5365GYKYAVK3ZUBWNTTEPSXEWN/graph.json","events_json":"https://pith.science/api/pith-number/5365GYKYAVK3ZUBWNTTEPSXEWN/events.json","paper":"https://pith.science/paper/5365GYKY"},"agent_actions":{"view_html":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN","download_json":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN.json","view_paper":"https://pith.science/paper/5365GYKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05061&json=true","fetch_graph":"https://pith.science/api/pith-number/5365GYKYAVK3ZUBWNTTEPSXEWN/graph.json","fetch_events":"https://pith.science/api/pith-number/5365GYKYAVK3ZUBWNTTEPSXEWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN/action/storage_attestation","attest_author":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN/action/author_attestation","sign_citation":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN/action/citation_signature","submit_replication":"https://pith.science/pith/5365GYKYAVK3ZUBWNTTEPSXEWN/action/replication_record"}},"created_at":"2026-07-05T10:20:10.944057+00:00","updated_at":"2026-07-05T10:20:10.944057+00:00"}