{"id":"W4319300975","doi":"10.1109/wacv56688.2023.00614","title":"HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":477,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Encoder; Segmentation; Artificial intelligence; Transformer; Convolutional neural network; Image segmentation; Pattern recognition (psychology); Scale-space segmentation; Computer vision; Voltage","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":[0.0006984437,0.0008606001,0.0005747876,0.001173266,0.0002207943,0.0009166923,0.001210288,0.0007821267,0.003728461],"category_scores_gemma":[0.001852143,0.0004569479,0.0008712527,0.0008297327,0.0004378281,0.001592288,0.00120758,0.0009369971,0.001248643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006980487,"about_ca_system_score_gemma":0.0009134675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002403599,"about_ca_topic_score_gemma":0.003735307,"domain_scores_codex":[0.9997501,0.00004242774,0.00001564388,0.00006648462,0.00009151317,0.0000338883],"domain_scores_gemma":[0.9997039,0.0001061766,0.00004708752,0.00007368007,0.00004553076,0.00002358508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000235444,0.00009698411,0.001013297,0.0001928239,0.00009367224,0.0001725672,0.0001080337,0.1431486,0.04572441,0.01348559,0.00922006,0.7865085],"study_design_scores_gemma":[0.00002013407,0.0000668748,0.0003443535,0.00001410616,0.0000256192,0.0001880834,0.00002309615,0.9619748,0.02405139,0.008865985,0.004407288,0.00001836721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006283891,0.000200929,0.9886516,0.00009737062,0.00002591119,0.00005763574,0.0001520447,0.003827668,0.0007029668],"genre_scores_gemma":[0.2516691,0.000521155,0.7411597,0.0002964265,0.00006708544,0.000156366,0.001283723,0.001088488,0.003758024],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003728461,"threshold_uncertainty_score":0.01247293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04367816882844694,"score_gpt":0.3724825427121474,"score_spread":0.3288043738837004,"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."}}