{"id":"W3216046900","doi":"10.48550/arxiv.2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Compute Canada","keywords":"Artificial intelligence; Computer science; Robustness (evolution); Segmentation; Image (mathematics); Computer vision; Pattern recognition (psychology); Object (grammar); Unsupervised learning; Image segmentation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0007342425,0.001450996,0.0008410087,0.0006708254,0.000246994,0.000594233,0.002070348,0.001357021,0.003669427],"category_scores_gemma":[0.001608252,0.000645504,0.001001234,0.0005063378,0.0009149275,0.000889793,0.001243777,0.001782274,0.001656109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000748028,"about_ca_system_score_gemma":0.0006458847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002660713,"about_ca_topic_score_gemma":0.005353304,"domain_scores_codex":[0.9996246,0.00008826754,0.00001163643,0.0001493675,0.00008597133,0.00004019178],"domain_scores_gemma":[0.9995168,0.0002101698,0.00004534226,0.0001477653,0.0000511834,0.00002859619],"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":[0.0002152365,0.0001058311,0.0008250427,0.0001523227,0.0001257677,0.0001374354,0.00008845192,0.7240314,0.02027838,0.01376665,0.01293923,0.2273342],"study_design_scores_gemma":[0.000009157387,0.00002291036,0.00008572289,0.000005938828,0.000005922567,0.00003642538,0.000003634937,0.9910138,0.002687735,0.005067389,0.001056248,0.000005036359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01136188,0.0003800342,0.9791712,0.0001657775,0.00007463169,0.00009603631,0.0002839921,0.005857554,0.002608842],"genre_scores_gemma":[0.3715991,0.0003911405,0.6140377,0.0005637832,0.0001136563,0.0003294575,0.002589131,0.001713005,0.008663159],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003669427,"threshold_uncertainty_score":0.01227552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04701729669888357,"score_gpt":0.1844635810616375,"score_spread":0.1374462843627539,"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."}}