{"id":"W4387582224","doi":"10.1016/j.imavis.2023.104838","title":"DiPS: Discriminative pseudo-label sampling with self-supervised transformers for weakly supervised object localization","year":2023,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ericsson (Canada); École de Technologie Supérieure; Artificial Intelligence in Medicine (Canada)","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Discriminative model; Artificial intelligence; Overfitting; Computer science; Pattern recognition (psychology); Transformer; Leverage (statistics); Classifier (UML); Novelty; Computer vision; Machine learning; Artificial neural network","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":[0.001686142,0.001381962,0.002003967,0.001226372,0.0007127992,0.001363183,0.003894195,0.001729213,0.006114946],"category_scores_gemma":[0.005770294,0.0008471924,0.001096423,0.001413348,0.001381969,0.002719191,0.003673218,0.002448142,0.003824394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008767692,"about_ca_system_score_gemma":0.001587597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003579796,"about_ca_topic_score_gemma":0.008266155,"domain_scores_codex":[0.9983973,0.000414503,0.0000702442,0.0004471641,0.0005064582,0.0001644387],"domain_scores_gemma":[0.9977126,0.0006803226,0.0001269868,0.0008747363,0.0004535299,0.0001518119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001382647,0.0005666905,0.001853544,0.000307884,0.0001519415,0.0001913247,0.0001736374,0.08330401,0.03399114,0.02238761,0.02000987,0.8356797],"study_design_scores_gemma":[0.00005028794,0.00008829756,0.0002126341,0.000008978094,0.00001542806,0.00007255143,0.0000222782,0.9758219,0.008567391,0.0134293,0.001697155,0.00001378254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004926346,0.0000688013,0.9899135,0.00005343121,0.00003015856,0.0000706896,0.0001977902,0.004342779,0.000396478],"genre_scores_gemma":[0.2452584,0.0001508955,0.7437998,0.0003625951,0.0001241921,0.0003459242,0.00333425,0.001239624,0.005384264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006114946,"threshold_uncertainty_score":0.02045655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03188130234756244,"score_gpt":0.3336098988760882,"score_spread":0.3017285965285257,"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."}}