{"id":"W2963537932","doi":"","title":"LF-Net: Learning Local Features from Images","year":2018,"lang":"en","type":"article","venue":"Infoscience (Ecole Polytechnique Fédérale de Lausanne)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Pipeline (software); Artificial intelligence; Exploit; Feature (linguistics); Computer vision; Process (computing); Differentiable function; Matching (statistics); Image (mathematics); Deep learning; Motion blur; Network architecture; Scratch; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006077564,0.0003164532,0.0002846821,0.0002955269,0.0006584837,0.000516142,0.002256976,0.000163887,0.0001386475],"category_scores_gemma":[0.0003026903,0.0003089719,0.000110331,0.001096761,0.0008264795,0.001988973,0.0008349502,0.0006142595,0.0002593978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441432,"about_ca_system_score_gemma":0.0002161658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004315717,"about_ca_topic_score_gemma":0.00005179499,"domain_scores_codex":[0.9971355,0.0001338085,0.0003796736,0.0008636384,0.00053206,0.000955302],"domain_scores_gemma":[0.9981667,0.0001843701,0.000212426,0.0009079733,0.0001960175,0.0003324693],"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":[0.00003353036,0.000143459,0.00549523,0.00001511413,0.00001475017,0.0001104752,0.001974387,0.0005470679,0.1841361,0.01377903,0.01983147,0.7739193],"study_design_scores_gemma":[0.0004536932,0.000509556,0.01425469,0.0002277818,0.00000835137,0.0001050583,0.0002747612,0.1494702,0.7476488,0.01508488,0.07100862,0.0009536862],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005180786,0.0002346733,0.9795853,0.001293681,0.0004492734,0.000246192,0.000007991749,0.001200707,0.01180133],"genre_scores_gemma":[0.6417767,0.00005639025,0.3529916,0.003047334,0.0002573865,0.00004638069,0.000003826944,0.00002364509,0.001796654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7729657,"threshold_uncertainty_score":0.9999362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006908288201830913,"score_gpt":0.2628354222947853,"score_spread":0.2559271340929544,"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."}}