{"id":"W3002047086","doi":"10.24963/ijcai.2020/120","title":"Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Pascal (unit); Embedding; Minimum bounding box; Computer vision; Shot (pellet); Object (grammar); Image segmentation; Scale-space segmentation; Segmentation-based object categorization; Bounding overwatch; Pixel; Pattern recognition (psychology); Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113904,0.001827861,0.001912555,0.001575329,0.000614327,0.001435679,0.003281382,0.002094549,0.002136764],"category_scores_gemma":[0.002481156,0.0008603283,0.001701541,0.001478521,0.00120943,0.003262367,0.002351677,0.002323815,0.001522822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260724,"about_ca_system_score_gemma":0.001045528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007224318,"about_ca_topic_score_gemma":0.01234443,"domain_scores_codex":[0.9988809,0.0001642277,0.00004161263,0.0006248404,0.0001523707,0.0001360804],"domain_scores_gemma":[0.9986645,0.0004866122,0.0001414839,0.0003221678,0.0002599757,0.0001253433],"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":[0.0008083507,0.0007350763,0.003893169,0.0004295612,0.0003520395,0.0002966444,0.0004976944,0.1757462,0.07559598,0.005994053,0.009675721,0.7259754],"study_design_scores_gemma":[0.00001197161,0.00008766939,0.000863363,0.0000145387,0.00003106794,0.00007151902,0.00004668657,0.9802874,0.01150252,0.005870547,0.001194282,0.00001840005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04520619,0.0007288304,0.9453709,0.0001913676,0.00009655457,0.0001220635,0.0002872337,0.00617819,0.001818556],"genre_scores_gemma":[0.579021,0.0004522208,0.4065956,0.0005979604,0.0001778023,0.000247119,0.00349534,0.0009737829,0.008439067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007224318,"threshold_uncertainty_score":0.01436454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0502827949639111,"score_gpt":0.3212738963088722,"score_spread":0.2709911013449611,"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."}}