{"id":"W4393154725","doi":"10.1609/aaai.v38i4.28069","title":"FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Health Industry Development Institute","keywords":"Computer vision; Rotation (mathematics); Artificial intelligence; Aerial image; Image (mathematics); Object (grammar); Computer science; Object detection; Computer graphics (images); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005811896,0.0002308199,0.0002427785,0.0002641832,0.0001122792,0.0005358099,0.001366208,0.0001045861,0.00003979206],"category_scores_gemma":[0.0006261866,0.0001817498,0.0001240659,0.001512834,0.000189384,0.001360519,0.0002997776,0.0004207042,0.00007396608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001151544,"about_ca_system_score_gemma":0.0001609499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009353288,"about_ca_topic_score_gemma":0.00003091875,"domain_scores_codex":[0.9980265,0.00002268119,0.0005588311,0.0005996606,0.0004465157,0.0003457816],"domain_scores_gemma":[0.9989869,0.00008802926,0.0001821205,0.0002694052,0.000414033,0.00005951003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006923383,0.00005062337,0.000006186929,0.00005805413,0.000006295674,0.000002959415,0.0008065098,0.000009067418,0.3484175,0.2960196,0.00003796828,0.3545159],"study_design_scores_gemma":[0.00001648059,0.0002003547,0.00006333827,0.0002839528,0.000004495109,0.000007886413,0.0001162003,0.04066239,0.7115749,0.2467807,0.0001330342,0.0001562531],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03181731,0.0001007984,0.956897,0.001974398,0.0009601737,0.0006173256,0.000006067019,0.0004097521,0.007217141],"genre_scores_gemma":[0.9835659,0.00009829798,0.01594151,0.00008618249,0.0001270903,0.0000628292,3.374456e-7,0.00001573306,0.0001021406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9517485,"threshold_uncertainty_score":0.741154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0508841076598038,"score_gpt":0.3249505792229302,"score_spread":0.2740664715631264,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}