Supplementary of Weak-shot Semantic Segmentation via Dual Similarity Transfer

In this appendix, we first clarify more details about the datasets, evaluation, and implementation in Section A1, Section A2, and Section A3. Afterwards, we provide more qualitative comparisons in Section A4. Then, we conduct more experiments about pixel-pixel similarity transfer in Section A5. Finally, we conduct experiments to explore the generalization ability of our model to dataset expansion in Section A6. These two datasets both contain enough classes and abundant images, which are appropriate for exploring the problem about transfer learning across classes. Specifically, COCO-Stuff-10K [1] totally covers 171 semantic-level classes.