{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001175094,0.0003277216,0.0002787256,0.0001199635,0.0003557715,0.0001178258,0.001336367,0.0002808492,0.000007365991],"category_scores_gemma":[0.00002356669,0.0003818644,0.0002705133,0.0006102053,0.00009282052,0.0002811627,0.001591454,0.0005193215,0.00005205889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003135044,"about_ca_system_score_gemma":0.0001188723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009455832,"about_ca_topic_score_gemma":0.00001834675,"domain_scores_codex":[0.9978231,0.00006817991,0.0001725205,0.001456933,0.0001176294,0.0003616357],"domain_scores_gemma":[0.9981963,0.000172318,0.0002645021,0.001011286,0.0001527627,0.0002028302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001041069,0.00007635198,0.0001404178,0.00006718729,0.00009479579,0.00007902144,0.00009426839,0.8607785,0.002135109,0.1333904,0.001639538,0.001400357],"study_design_scores_gemma":[0.0006905961,0.0001051279,0.0005765218,0.00003753971,0.00004351533,0.000009792812,0.00001039578,0.6538068,0.003756748,0.3308019,0.009596359,0.0005647127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03732129,0.00004869477,0.9596346,0.0008394881,0.0005852989,0.0008958906,0.00004544818,0.0003956608,0.0002336449],"genre_scores_gemma":[0.9696364,0.00002800829,0.02870494,0.0003925406,0.0002153381,0.00001821012,0.00004287041,0.0000270797,0.0009346373],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9323151,"threshold_uncertainty_score":0.9998633,"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."}}