{"id":"W4402727719","doi":"10.1109/cvpr52733.2024.02215","title":"Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; University of British Columbia","funders":"","keywords":"Shot (pellet); Computer science; Computer vision; Artificial intelligence; Segmentation; Scale (ratio); Image segmentation; One shot; Computer graphics (images); Engineering; Geography; Cartography; Materials science","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":[0.0004341046,0.0001403311,0.0001334099,0.0001183605,0.0001922494,0.0006606259,0.0003002479,0.00005010147,0.00006414225],"category_scores_gemma":[0.00002266668,0.0001209746,0.0001022712,0.0003737381,0.00002321986,0.0005239704,0.0000937068,0.0001051933,0.00007778926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000443347,"about_ca_system_score_gemma":0.00007135447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001024831,"about_ca_topic_score_gemma":0.00000400786,"domain_scores_codex":[0.998688,0.00005887323,0.0002501674,0.0004964726,0.0002267864,0.0002797297],"domain_scores_gemma":[0.9995362,0.00009601681,0.000042241,0.0001724999,0.00005983915,0.00009326204],"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":[0.00006318939,0.0007013485,0.0005282182,0.000898493,0.0002507574,0.00003015601,0.0267054,0.01048995,0.08748232,0.29704,0.009912953,0.5658973],"study_design_scores_gemma":[0.0006377757,0.00005072626,0.0001441374,0.00001523727,0.000008769665,0.0000104725,0.000398085,0.9848404,0.002047526,0.0002029988,0.01146101,0.0001828455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002807354,0.0001601358,0.9889908,0.0004706548,0.000399236,0.0004907862,0.000001419821,0.0006829214,0.005996652],"genre_scores_gemma":[0.1003739,0.000003929649,0.8890955,0.0004927455,0.0001394691,0.0001986238,0.00002474679,0.0000192855,0.009651735],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9743505,"threshold_uncertainty_score":0.6370431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07399787078156803,"score_gpt":0.3490467313407939,"score_spread":0.2750488605592258,"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."}}