Figure 1. ZS3 aims to train a model merely on seen classes and
generalize it to classes that have not been seen in the training (un-
seen classes). Existing methods formulate it as a pixel-level zero-
shot classification problem (b), and use semantic features from a
language model to transfer the knowledge from seen classes to
unseen ones. In contrast, as in (c), we decouple ZS3 into two
sub-tasks: 1) A class-agnostic grouping and 2) A segment-level
zero-shot classification, which enables us to take full advantage of
the pre-trained vision-language model.