{"id":"W4312509687","doi":"10.1109/iscas48785.2022.9937894","title":"DSegAN: A Deep Light-weight Segmentation-based Attention Network for Image Restoration","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Computer science; Feature (linguistics); Image restoration; Benchmark (surveying); Discriminative model; Image segmentation; Computer vision; Pattern recognition (psychology); Segmentation; Image (mathematics); Feature detection (computer vision); Pixel; Feature extraction; Image texture; Image processing; Geography; Cartography","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":[0.0002890953,0.000800951,0.0005880046,0.0005907042,0.000240575,0.0004210444,0.001331549,0.0007463646,0.002400661],"category_scores_gemma":[0.0005511824,0.0002715424,0.0005127623,0.0003914243,0.0004315062,0.0007005919,0.0008958879,0.0009725241,0.0005892712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007151632,"about_ca_system_score_gemma":0.0006455988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005991236,"about_ca_topic_score_gemma":0.01053225,"domain_scores_codex":[0.9998732,0.000013141,0.000004716329,0.00003472627,0.00004650799,0.00002774443],"domain_scores_gemma":[0.9998863,0.00002534123,0.00001582617,0.00001822869,0.00003861859,0.00001572114],"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":[0.0004611855,0.0002579388,0.0009844986,0.000204577,0.0001532693,0.0002111477,0.0000757853,0.2050127,0.07332343,0.005017853,0.01138457,0.7029132],"study_design_scores_gemma":[0.00002046513,0.0001134354,0.0004151724,0.00001298403,0.00003932185,0.0001042813,0.00001128848,0.9723681,0.01997207,0.002939146,0.0039891,0.0000145662],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05022139,0.002297101,0.9356015,0.0003949518,0.0002283586,0.0001131283,0.0002712002,0.005611082,0.005261205],"genre_scores_gemma":[0.67064,0.001310591,0.3033462,0.0009446847,0.0001081227,0.0001382005,0.001171097,0.000425684,0.02191542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005991236,"threshold_uncertainty_score":0.01191276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01747603524583953,"score_gpt":0.2746711991238214,"score_spread":0.2571951638779819,"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."}}