Semantic Mismapping in Generalized Category Discovery: Evaluation and Mitigation
arXiv:2610.39356v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to perform old-category recognition and novel-category discovery in the same unlabeled set. Early methods address both objectives through clustering and evaluate the exchangeable predicted indices with global Hungarian (GH) matching. Recent methods adopt trainable parametric heads, using supervision for old-category recognition and discovery-oriented objectives for new categories. In this way, the output…