{"id":"W7106039670","doi":"10.2139/ssrn.5635890","title":"ECA-UNet: Efficient Channel Attention Enhanced U-Net for Image Segmentation","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Segmentation; Image segmentation; Kernel (algebra); Channel (broadcasting); Encoder; Scale-space segmentation; Image (mathematics); Segmentation-based object categorization; Deep 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","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002920192,0.0009837159,0.000854824,0.0005821957,0.001681015,0.0006754328,0.002762175,0.0004654079,0.00001785734],"category_scores_gemma":[0.0001030325,0.001071681,0.0008704162,0.001161431,0.000177091,0.0006182219,0.001066674,0.005270606,0.00008027103],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004852495,"about_ca_system_score_gemma":0.0053614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001790885,"about_ca_topic_score_gemma":0.0001365068,"domain_scores_codex":[0.9894019,0.0003582712,0.001743981,0.001979657,0.0009036951,0.005612488],"domain_scores_gemma":[0.9949111,0.0003667492,0.002085272,0.001311876,0.001030881,0.0002941715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004158208,0.0009570601,0.000009487967,0.0003424365,0.0009816088,0.000004622179,0.001155431,0.3863334,0.04295468,0.2331339,0.0005041383,0.3332073],"study_design_scores_gemma":[0.003152057,0.0008134065,0.00008162591,0.0005583504,0.0003866959,0.0002672401,0.0008942718,0.462072,0.01388181,0.5152514,0.001234622,0.001406523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009734337,0.00278284,0.9770825,0.003193311,0.002914654,0.003559477,0.00007511085,0.0001688488,0.0004889568],"genre_scores_gemma":[0.8687367,0.02831612,0.08039074,0.0005354681,0.003178618,0.002435907,0.0003935956,0.0001775439,0.01583525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8966917,"threshold_uncertainty_score":0.9996186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114368188893866,"score_gpt":0.2900059892649676,"score_spread":0.278569170375581,"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."}}