{"id":"W4394758452","doi":"10.1007/s11633-023-1385-0","title":"Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications","year":2024,"lang":"en","type":"article","venue":"Machine Intelligence Research","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":187,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Segmentation; Computer science; Data science; Code (set theory); Artificial intelligence; Human–computer interaction; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007430455,0.001733813,0.001217652,0.003022571,0.001106051,0.00229118,0.00241261,0.002746099,0.002571125],"category_scores_gemma":[0.01505703,0.0004997403,0.001455924,0.002155458,0.001626016,0.002769826,0.001707443,0.002330151,0.001168986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001712192,"about_ca_system_score_gemma":0.001095444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0130536,"about_ca_topic_score_gemma":0.02217448,"domain_scores_codex":[0.9969667,0.001063721,0.0001869374,0.001112112,0.0004081355,0.0002624684],"domain_scores_gemma":[0.9929584,0.004259717,0.0003656749,0.00130365,0.0007638237,0.0003486781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003718569,0.001223721,0.06253307,0.003115605,0.001328733,0.001126778,0.001187796,0.3779569,0.01768798,0.01335295,0.1037485,0.4130194],"study_design_scores_gemma":[0.0001046565,0.0006147067,0.01275122,0.0002211855,0.0001541168,0.0005131014,0.0007238723,0.9447931,0.008943602,0.01516242,0.01595205,0.00006596812],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7944717,0.01628597,0.1347635,0.008536069,0.001435701,0.0004991113,0.01240664,0.01389259,0.0177088],"genre_scores_gemma":[0.8555496,0.001611794,0.1121438,0.001575728,0.0002762208,0.000141297,0.02422988,0.001051791,0.003419907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0130536,"threshold_uncertainty_score":0.03929645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.108779578790394,"score_gpt":0.4174717492934924,"score_spread":0.3086921705030984,"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."}}