{"id":"W2965242851","doi":"10.48550/arxiv.1805.11123","title":"Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Overfitting; Pooling; Computer science; Artificial intelligence; Convolutional neural network; Generalization; Inference; Pattern recognition (psychology); Focus (optics); Object (grammar); Deep learning; Machine learning; Artificial neural network; Mathematics","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":[0.0005135997,0.0001152295,0.000163967,0.00008199082,0.0001540004,0.00004912704,0.0005436883,0.00004799318,0.00000346088],"category_scores_gemma":[0.00006931169,0.0001120165,0.00005235795,0.0009009868,0.0000698466,0.0004007586,0.0001362112,0.00003563653,0.000004200511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005341398,"about_ca_system_score_gemma":0.0001045866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001267247,"about_ca_topic_score_gemma":0.0003036336,"domain_scores_codex":[0.9990426,0.00008928391,0.0001208014,0.0004178684,0.00005945611,0.0002699704],"domain_scores_gemma":[0.9990037,0.00009417874,0.0001601852,0.0004417602,0.0002467482,0.00005339316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005375882,0.0003887114,0.4863804,0.0002306918,0.0003043618,0.0001718293,0.0004941142,0.02416339,0.001209199,0.4759041,0.002808027,0.00740756],"study_design_scores_gemma":[0.006583934,0.001185936,0.06581816,0.0001447395,0.0001814018,0.00003852386,0.0001613129,0.8803047,0.01459259,0.01689931,0.01299931,0.001090067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2022298,0.00001742851,0.7970371,0.00001658497,0.0001015882,0.0001147959,0.0001015555,0.00006339759,0.0003177263],"genre_scores_gemma":[0.9523893,0.00001064892,0.04734051,0.00008641686,0.00006345526,3.448076e-7,0.00003866032,0.000006307967,0.00006435222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8561413,"threshold_uncertainty_score":0.4567901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06881288877122635,"score_gpt":0.2382420283306845,"score_spread":0.1694291395594582,"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."}}