{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004435034,0.0003544748,0.0004334071,0.0005461372,0.0004239651,0.0001786107,0.001517102,0.000185343,0.00008287039],"category_scores_gemma":[0.00002450139,0.000350309,0.0002811537,0.001728015,0.0003068897,0.0006862064,0.0002733899,0.0003650018,0.0002670192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009177534,"about_ca_system_score_gemma":0.0002077106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572975,"about_ca_topic_score_gemma":0.00002637056,"domain_scores_codex":[0.9964584,0.0001118514,0.0009973837,0.001071919,0.000801135,0.0005593327],"domain_scores_gemma":[0.997299,0.000589075,0.0003319196,0.0009749351,0.0004540852,0.0003510444],"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":[0.0001646433,0.00144636,0.000160699,0.0002326445,0.0001789688,0.00001138309,0.001574857,0.01009776,0.1095349,0.054305,0.01982262,0.8024701],"study_design_scores_gemma":[0.001164096,0.0002427716,0.0006318408,0.0001188316,0.00002434783,0.00001714417,0.00009752841,0.9798535,0.008594164,0.005955681,0.002929886,0.0003701838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00468381,0.000009815155,0.9864501,0.005491118,0.0003383564,0.002099939,0.0001118199,0.000449897,0.0003650807],"genre_scores_gemma":[0.2641385,0.0001668498,0.731347,0.0007899248,0.000400765,0.002129032,0.0003572732,0.0000765506,0.0005940708],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9697558,"threshold_uncertainty_score":0.9998949,"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."}}