{"id":"W4319323278","doi":"10.48550/arxiv.2302.01403","title":"Self-Supervised Relation Alignment for Scene Graph Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Scene graph; Graph; Message passing; Artificial intelligence; Regularization (linguistics); Machine learning; Pattern recognition (psychology); Theoretical computer science; Parallel computing","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":[0.0005993202,0.000865336,0.0005550655,0.0006739467,0.0004126187,0.0005094174,0.002040477,0.0009176614,0.004273501],"category_scores_gemma":[0.002127671,0.0004231873,0.000695958,0.0005921605,0.0006159252,0.001708993,0.001143834,0.001552906,0.001724682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006798756,"about_ca_system_score_gemma":0.0007043029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002612482,"about_ca_topic_score_gemma":0.00745645,"domain_scores_codex":[0.9994926,0.0001242824,0.0000131323,0.0002215858,0.0001080579,0.00004031134],"domain_scores_gemma":[0.9991927,0.000260388,0.00008762206,0.0002836051,0.0001304185,0.00004520064],"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":[0.0003216236,0.0002906411,0.00208594,0.0002026959,0.00009470352,0.0001918238,0.0002043572,0.3416875,0.06046773,0.02657161,0.01472347,0.5531579],"study_design_scores_gemma":[0.000008295838,0.00002920675,0.0001943515,0.000003582828,0.000006288874,0.00003771584,0.00001366576,0.9817812,0.009095938,0.007674186,0.001149933,0.000005517593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02149173,0.0001009715,0.9691928,0.0001370444,0.00003553274,0.00005979957,0.0001952041,0.007295426,0.001491429],"genre_scores_gemma":[0.4149508,0.0001091142,0.5761488,0.0002904423,0.00005636326,0.000138035,0.001937444,0.0012774,0.00509164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004273501,"threshold_uncertainty_score":0.01429629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1117332198758273,"score_gpt":0.2218685285960819,"score_spread":0.1101353087202545,"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."}}