Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery

1 code implementation • 26 Aug 2023 • Qiang Li, Qiuyang Ma, Weizhi Nie, AnAn Liu

We employed a clustering method with varying constraint conditions, ranging from strict to loose, allowing for the generation of dependable labels for a subset of unlabeled data during the training phase.

Novel Class Discovery reinforcement-learning +1