{"id":"W4386243190","doi":"10.1109/crv60082.2023.00014","title":"Sparse Shape Encoding for Topologically Improved Instance Segmentation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Encoding (memory); Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); ENCODE; Sparse approximation; Neural coding; Representation (politics); Object (grammar); Inference; Benchmark (surveying); 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":[],"consensus_categories":[],"category_scores_codex":[0.0002102292,0.00008007439,0.00008963267,0.00006713194,0.0001041578,0.0000768832,0.000323352,0.00003733305,0.00001753059],"category_scores_gemma":[0.0001181483,0.0000653311,0.00004432238,0.0004460841,0.00002086771,0.0006200385,0.0001338275,0.00004650339,0.00002678588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002773901,"about_ca_system_score_gemma":0.00001858677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002711495,"about_ca_topic_score_gemma":0.000002292424,"domain_scores_codex":[0.9992572,0.00001182252,0.0001498715,0.0002699368,0.00009166148,0.0002194839],"domain_scores_gemma":[0.9995165,0.0001196716,0.00005012789,0.0002054224,0.00006894679,0.00003933527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001819457,0.00002606332,0.0001638603,0.00002232983,0.000007245518,0.000008774963,0.000202617,0.00001000585,0.3000147,0.1160777,0.002917982,0.5805305],"study_design_scores_gemma":[0.0004922998,0.0003990392,0.001011837,0.00001819456,0.000003643123,0.000004475806,0.0001241459,0.1650709,0.7413405,0.07737854,0.01382899,0.0003274338],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003265855,0.00002065101,0.9917066,0.0006863467,0.0001200264,0.0003352002,0.000001765265,0.001199968,0.002663658],"genre_scores_gemma":[0.2776183,0.0001335771,0.7191383,0.001071852,0.00006079075,0.0001215955,0.000007077561,0.000008357326,0.001840153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5802031,"threshold_uncertainty_score":0.2664125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05150319186733135,"score_gpt":0.3346912540587555,"score_spread":0.2831880621914242,"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."}}