{"id":"W4281679836","doi":"10.48550/arxiv.2206.02424","title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":257,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Convolution (computer science); Detector; Code (set theory); State (computer science); Task (project management); Object detection; Computer engineering; Separable space; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Real-time computing; Simulation; Computer vision; Embedded system; Algorithm; Pattern recognition (psychology); Programming language; Telecommunications; Engineering; Artificial neural network","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":[0.0001923582,0.0004803263,0.0004568373,0.0002552719,0.0004958251,0.000110765,0.003401431,0.0002252997,0.0001055839],"category_scores_gemma":[0.0000342115,0.0005556172,0.0003211626,0.0007945189,0.0001034993,0.0001711231,0.002565536,0.0006702641,0.00006893018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003234665,"about_ca_system_score_gemma":0.0001968771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003420257,"about_ca_topic_score_gemma":0.000005280019,"domain_scores_codex":[0.9969415,0.0002125011,0.0002829256,0.001812373,0.0001429121,0.0006077585],"domain_scores_gemma":[0.9966277,0.0006813426,0.0003986077,0.001939759,0.0001034726,0.0002491564],"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":[0.0001943107,0.0002236333,0.00007803739,0.0001000619,0.0002040222,0.00011531,0.0003178191,0.9022565,0.006589205,0.06651682,0.0213583,0.002045937],"study_design_scores_gemma":[0.0008419895,0.0002978526,0.0000785503,0.00004212205,0.000109626,0.000009324968,0.00001298253,0.7796748,0.005092023,0.1930767,0.01958575,0.001178225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03926038,0.00008953075,0.9565142,0.0003547272,0.0003105346,0.001646703,0.0001290054,0.0007700485,0.0009249112],"genre_scores_gemma":[0.8815064,0.0003209407,0.1080181,0.0003184775,0.0002514292,0.0001398661,0.0001309088,0.0001152742,0.009198549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8484961,"threshold_uncertainty_score":0.9996895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05051061162297856,"score_gpt":0.2040788356219474,"score_spread":0.1535682239989688,"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."}}