{"id":"W4404166222","doi":"10.1007/978-3-031-72855-6_7","title":"Sparse Refinement for Efficient High-Resolution Semantic Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Resolution (logic); Natural language processing; Pattern recognition (psychology); Computer vision; Information retrieval","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"],"consensus_categories":[],"category_scores_codex":[0.0004806663,0.0004427799,0.000349664,0.0006026864,0.0003049953,0.0003682852,0.001698654,0.0001742639,0.000007939734],"category_scores_gemma":[0.00002765823,0.0004116092,0.0001242034,0.0007158747,0.0003003423,0.0002389811,0.0008773386,0.0004268044,0.00009329215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005607206,"about_ca_system_score_gemma":0.0002018766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009641188,"about_ca_topic_score_gemma":0.00004322365,"domain_scores_codex":[0.9964417,0.00001330678,0.0005327371,0.001668807,0.0007488269,0.0005946782],"domain_scores_gemma":[0.9979117,0.0003725871,0.0002498374,0.001146588,0.000194553,0.0001247266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004304487,0.00002334428,8.465949e-7,0.00005593787,0.000007805826,0.0000108135,0.00014439,0.5595074,0.0005299009,0.1773479,0.00006772469,0.2622996],"study_design_scores_gemma":[0.000172346,0.0001082027,0.00001038966,0.0002210224,0.00001469914,0.00001651416,8.246363e-8,0.7596406,0.001647669,0.2359782,0.001838505,0.0003517777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007816267,0.0005064058,0.9929868,0.002238645,0.002174891,0.001265287,0.00001469666,0.0002841718,0.0004509184],"genre_scores_gemma":[0.06884921,0.00005430935,0.9282077,0.0009240817,0.0006904813,0.0001809839,0.00003694919,0.00005540686,0.001000867],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2619478,"threshold_uncertainty_score":0.9998336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02168482752635507,"score_gpt":0.2712635171816526,"score_spread":0.2495786896552975,"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."}}