{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003522478,0.0003781623,0.0003887331,0.0002426112,0.0002605077,0.001067422,0.0004187137,0.0001679118,0.00007341724],"category_scores_gemma":[0.00002973708,0.0003473223,0.00009189239,0.000336912,0.00007248857,0.0006047035,0.0005469652,0.0004991961,0.00004036592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001048757,"about_ca_system_score_gemma":0.0002018571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001379765,"about_ca_topic_score_gemma":0.00001747193,"domain_scores_codex":[0.9974973,0.0001837492,0.0004090005,0.000986974,0.000597081,0.0003259117],"domain_scores_gemma":[0.9989694,0.00007833284,0.0002953403,0.0003251083,0.0001353511,0.0001964134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007445914,0.0009135373,0.06495039,0.004657856,0.001838201,0.0006646623,0.05838106,0.0534618,0.6556208,0.03418722,0.001778541,0.1228014],"study_design_scores_gemma":[0.0008726027,0.0001828586,0.008997043,0.0002329836,0.0000673755,0.00005284515,0.001268774,0.9855157,0.001659855,0.0004471577,0.0001066613,0.0005961745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3041279,0.00003988481,0.6927413,0.0005020555,0.0002153972,0.0004339623,0.000002180007,0.0003162229,0.001621094],"genre_scores_gemma":[0.858974,0.00002573302,0.1399077,0.0006155052,0.00008518476,0.00001942478,0.00007749035,0.00003467157,0.0002603363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9320539,"threshold_uncertainty_score":0.9999695,"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."}}