{"id":"W4380421145","doi":"10.20944/preprints202306.0899.v1","title":"CoSOV1Net: Cone- and Spatial-Opponency Primary Visual Cortex-Inspired Neural Network for Lightweight Salient Object Detection","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Salient; Object detection; Computer vision; Pattern recognition (psychology); Artificial neural network; Visual cortex; Human visual system model; Object (grammar); Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001342557,0.0006560282,0.0007651541,0.0003468807,0.0005572824,0.0002345245,0.001019042,0.0005654792,0.00003977722],"category_scores_gemma":[0.0002108476,0.0006872576,0.0004171561,0.0004827457,0.0001249066,0.0003562997,0.002913178,0.0008348118,0.0003490082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002733578,"about_ca_system_score_gemma":0.0001910864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005268511,"about_ca_topic_score_gemma":0.000369421,"domain_scores_codex":[0.9948092,0.0003485111,0.001103004,0.002231736,0.0007094999,0.0007981004],"domain_scores_gemma":[0.9970931,0.0001985098,0.000727833,0.001275396,0.0003929237,0.0003121958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001753425,0.001997021,0.357666,0.004145691,0.001813381,0.000225351,0.005945706,0.01542478,0.2230455,0.005841226,0.001748865,0.3803931],"study_design_scores_gemma":[0.001185082,0.000390411,0.7527048,0.0002747194,0.0001172252,0.00003430244,0.00002993109,0.21678,0.01663566,0.008676306,0.002061642,0.001109938],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7406346,0.0001775482,0.246698,0.0007279906,0.007761293,0.002148397,0.00002638924,0.001464666,0.0003610848],"genre_scores_gemma":[0.9954374,0.0002625872,0.001059143,0.0004869053,0.0007780533,0.0007507743,0.00009985997,0.00008909524,0.001036183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3950388,"threshold_uncertainty_score":0.9995579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08197928972799307,"score_gpt":0.3328203199680017,"score_spread":0.2508410302400086,"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."}}