{"id":"W3137661749","doi":"10.48550/arxiv.2103.13998","title":"GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Bottleneck; Artificial intelligence; Task (project management); Grid; Synthetic data; Block (permutation group theory); Process (computing); Transfer of learning; Scale (ratio); Pattern recognition (psychology); Machine learning","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":[0.000377781,0.000611514,0.0006170056,0.0002193985,0.0003092078,0.0004640939,0.00222826,0.0003601731,0.00002288773],"category_scores_gemma":[0.00001730071,0.0006901642,0.0002747006,0.000814228,0.0001949573,0.001317681,0.001016416,0.0006283264,0.0000134128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003469789,"about_ca_system_score_gemma":0.0003430436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004363598,"about_ca_topic_score_gemma":0.0006285844,"domain_scores_codex":[0.9964318,0.0002299454,0.0003393865,0.002034084,0.0001246268,0.0008401194],"domain_scores_gemma":[0.9971578,0.0001176872,0.0001698277,0.001750047,0.0005559077,0.0002487264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009640802,0.007563728,0.001297801,0.002465216,0.001421726,0.001917097,0.01603895,0.1438548,0.7442685,0.03326754,0.002269504,0.04467107],"study_design_scores_gemma":[0.002777412,0.0009973374,0.0003268874,0.001057619,0.0003450637,0.00001889904,0.0003569689,0.5611385,0.4264419,0.003285346,0.0007152949,0.002538841],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1093361,0.0001256809,0.8867846,0.0000256316,0.0005370484,0.001007289,0.00001810534,0.0008535575,0.001311988],"genre_scores_gemma":[0.7529146,0.00006758935,0.2461269,0.0000708352,0.0001737882,0.00001990487,0.00007186287,0.00005793474,0.0004965913],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6435785,"threshold_uncertainty_score":0.9995549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05724932680637841,"score_gpt":0.2089858899274059,"score_spread":0.1517365631210275,"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."}}