{"id":"W2798956329","doi":"10.1109/cvpr.2018.00140","title":"HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Hash function; Computer science; Feature hashing; Artificial intelligence; Deep learning; Double hashing; Pairwise comparison; Overfitting; Pattern recognition (psychology); Similarity (geometry); Image retrieval; Hash table; Image (mathematics); Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001529756,0.0001257638,0.0001196125,0.00009548626,0.0002101192,0.0001402131,0.0004630115,0.00003711413,0.0001508051],"category_scores_gemma":[0.00006000682,0.00009664849,0.00002945279,0.0004617635,0.00008472569,0.0006689198,0.0001317679,0.0001252723,0.0003545604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003430468,"about_ca_system_score_gemma":0.00003396513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001290025,"about_ca_topic_score_gemma":0.00002383735,"domain_scores_codex":[0.9989496,0.00003208081,0.0001293012,0.0003562145,0.0002616918,0.000271146],"domain_scores_gemma":[0.9992543,0.00004524917,0.00004476057,0.0003099097,0.0002113528,0.0001343738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000212528,0.0003536272,0.00933483,0.00004793131,0.0001350976,0.0002634478,0.003890152,0.0004771289,0.05703755,0.2869304,0.02936912,0.6119482],"study_design_scores_gemma":[0.0005641205,0.003234737,0.004214067,0.00006277912,0.000007778874,0.00008839068,0.0002025013,0.01523543,0.7662122,0.01293827,0.1965578,0.0006819864],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004285478,0.00001287103,0.9826965,0.0009515951,0.00003933081,0.000136157,4.408556e-7,0.0007210057,0.01115663],"genre_scores_gemma":[0.6730562,0.000001630134,0.3222807,0.001440005,0.00009154013,0.00001177821,0.000002871514,0.000009574836,0.003105708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7091746,"threshold_uncertainty_score":0.4557275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01091868193366021,"score_gpt":0.266492953822883,"score_spread":0.2555742718892228,"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."}}