{"id":"W4408609686","doi":"10.1109/tpami.2025.3553051","title":"Generating Inverse Feature Space for Class Imbalance in Point Cloud Semantic Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Point cloud; Class (philosophy); Feature (linguistics); Pattern recognition (psychology); Point (geometry); Space (punctuation); Feature vector; Mathematics; Geometry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008390357,0.001174857,0.0009669349,0.001104333,0.000636197,0.000995763,0.001944864,0.001263923,0.001362249],"category_scores_gemma":[0.002721226,0.0005097841,0.0008257622,0.001172228,0.001037208,0.00220148,0.002138169,0.001764852,0.0004827061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108566,"about_ca_system_score_gemma":0.001046648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005366502,"about_ca_topic_score_gemma":0.007436787,"domain_scores_codex":[0.9994913,0.00005677402,0.00001972448,0.0001929074,0.0001493446,0.00008992182],"domain_scores_gemma":[0.9993764,0.0001580163,0.00008018887,0.0001813603,0.0001542646,0.00004987652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004797377,0.0002545931,0.006151753,0.0001003111,0.0001079427,0.0002124325,0.0003077906,0.5240983,0.02851896,0.007632244,0.005619327,0.4265167],"study_design_scores_gemma":[0.0000109132,0.0000405756,0.0006097422,0.000004167819,0.00000814504,0.00003759529,0.00002620372,0.9899743,0.004724815,0.00403534,0.0005214656,0.000006642199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1872565,0.0002878691,0.8065967,0.0002939566,0.00005718344,0.00009753752,0.0003200924,0.003374174,0.001715914],"genre_scores_gemma":[0.8602563,0.0001177936,0.1361937,0.0001755989,0.00003758306,0.0001197109,0.001445483,0.0002288964,0.001425013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005366502,"threshold_uncertainty_score":0.01067054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00989755084483435,"score_gpt":0.2608261349817829,"score_spread":0.2509285841369486,"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."}}