{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001188351,0.0004088192,0.0004270946,0.0008104994,0.0007824057,0.001394462,0.003344184,0.00009258786,0.00008127015],"category_scores_gemma":[0.00008790592,0.0004218706,0.00005366974,0.0006934777,0.0002547155,0.0009874256,0.00608682,0.0009498888,0.00001419525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003170581,"about_ca_system_score_gemma":0.0001669197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004186618,"about_ca_topic_score_gemma":0.0002794228,"domain_scores_codex":[0.996669,0.00007220263,0.0004947395,0.001561406,0.0007107958,0.0004918533],"domain_scores_gemma":[0.9976104,0.0008016409,0.0003861313,0.0009729954,0.00007941149,0.0001494603],"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":[0.000004022987,0.00002053155,0.0001729582,0.00004814543,0.000009481935,0.00004746192,0.001989627,0.1457738,0.001661329,0.004504987,0.000003752336,0.8457639],"study_design_scores_gemma":[0.000309754,0.00008074886,0.0006042104,0.0002197868,0.000008052276,0.00009118264,8.822569e-7,0.9885008,0.0002061519,0.00930554,0.0002172106,0.0004556964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006576559,0.000220953,0.9943613,0.000948119,0.0005893912,0.0007652923,0.000003792748,0.0001791625,0.002274286],"genre_scores_gemma":[0.4972997,0.000008883276,0.5014739,0.000813862,0.000136668,0.00003684229,0.000009791543,0.00003439711,0.0001859805],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8453082,"threshold_uncertainty_score":0.9998233,"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."}}