{"id":"W4312330522","doi":"10.1007/978-3-031-20044-1_16","title":"Open-World Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Pipeline (software); Cluster analysis; Image segmentation; Encoder; Embedding; Semantics (computer science); Object (grammar); Segmentation-based object categorization; Natural language processing; Pattern recognition (psychology); Scale-space segmentation; Computer vision","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":[0.000691706,0.001352916,0.001205206,0.002267055,0.0008713321,0.003275024,0.002303997,0.001754453,0.00547199],"category_scores_gemma":[0.001740056,0.0007438432,0.001732822,0.002875979,0.001300005,0.004079548,0.003314484,0.001897169,0.00487588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101916,"about_ca_system_score_gemma":0.001422079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005071366,"about_ca_topic_score_gemma":0.007852389,"domain_scores_codex":[0.9992219,0.0001083923,0.00003897307,0.0003489811,0.0001496068,0.0001321085],"domain_scores_gemma":[0.9994121,0.0001321515,0.00004644692,0.0001870335,0.0001676109,0.00005470051],"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":[0.0003699151,0.0002184999,0.0007814466,0.0002622985,0.000118693,0.0002679955,0.0004323989,0.0525857,0.06055855,0.05107369,0.01013678,0.823194],"study_design_scores_gemma":[0.00001804569,0.00008401264,0.0006774464,0.00004312673,0.00005509631,0.000238575,0.0002739061,0.8843312,0.03514801,0.06985798,0.009223359,0.00004931793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01313792,0.0002645361,0.978852,0.0001339848,0.00007639943,0.00006768751,0.0002736162,0.003353055,0.003840782],"genre_scores_gemma":[0.2505679,0.0005294568,0.7360241,0.000193082,0.00009698131,0.000139749,0.003062142,0.001527667,0.007858878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00547199,"threshold_uncertainty_score":0.01830566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362282984824621,"score_gpt":0.3093973092282888,"score_spread":0.2957744793800426,"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."}}