FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss

arXiv:2610.39423 · cs.CV, cs.AI, cs.LG, cs.NE · Submitted 2026-10-29 · Read on arXiv

cs.CV, cs.AI, cs.LG, cs.NE

Submitted: 2026-10-29

Updated: 2026-10-29

Comments: Accepted to WACV 2027. 24 pages (11 main + 13 supplementary). Project page: https://shineiarakawa.github.io/fdsml/

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Related papers