Abstract: FSCIL (Few-shot class-incremental learning) is a prominent research topic in the ML community. It faces two significant challenges: forgetting old class knowledge and overfitting to limited ...

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...

Abstract: Recently graph auto-encoders have received increasingly widespread attention as one of the important models in the field of deep learning. Existing graph auto-encoder models only use graph ...