{"id":"W3101401226","doi":"10.48550/arxiv.2011.07205","title":"Bi-Dimensional Feature Alignment for Cross-Domain Object Detection","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Domain (mathematical analysis); Computer science; Benchmark (surveying); Artificial intelligence; Dimension (graph theory); Object detection; Feature (linguistics); Divergence (linguistics); Object (grammar); Pattern recognition (psychology); Channel (broadcasting); Representation (politics); Computer vision; Exploit; Feature extraction; Mathematics; Geography; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001793479,0.001217395,0.001439845,0.001945976,0.0005833863,0.001199209,0.002043545,0.001340616,0.002117957],"category_scores_gemma":[0.00377211,0.0004640429,0.001094527,0.002087516,0.0008166677,0.002305034,0.002497475,0.001952889,0.001694043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006746806,"about_ca_system_score_gemma":0.0007460585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001935636,"about_ca_topic_score_gemma":0.002184019,"domain_scores_codex":[0.9984311,0.0003026018,0.00007010223,0.0006897529,0.0003227964,0.0001835455],"domain_scores_gemma":[0.9982968,0.0004656995,0.0002080091,0.0004928143,0.0004520224,0.00008475318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005087593,0.0004265959,0.00635075,0.0001785086,0.0002800688,0.0002270944,0.0001812433,0.09549862,0.06026803,0.007347917,0.00732697,0.8214055],"study_design_scores_gemma":[0.00001396875,0.0001165839,0.002816177,0.00001230909,0.00004410369,0.000239466,0.0000562295,0.9632611,0.02174599,0.008446202,0.003221826,0.00002602046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03177247,0.000538348,0.9644297,0.00009935835,0.00005200634,0.00004701447,0.0001328041,0.001887008,0.001041231],"genre_scores_gemma":[0.6168334,0.0003754963,0.376105,0.0003639646,0.00009741804,0.0001424308,0.001566877,0.0003640393,0.004151407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002117957,"threshold_uncertainty_score":0.009484887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0574827531333036,"score_gpt":0.2213925375591742,"score_spread":0.1639097844258706,"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."}}