Semantic segmentation aims to acquire a detailed understanding of images . In practical scenarios, new categories that are different from the categories in training usually appear . In this paper, we propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation . Our method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training . We conduct comprehensive experiments on diverse split s of the PASCAL dataset. The experimental results clearly demonstrate the effectiveness of our method. ┬áThe experimental results . clearly demonstrate that our method is effective in our method’s effectiveness of using the experimental results. The research is published in the journal Computer Vision, published by Springer, on Tuesday, October 26, at $1.99/PASP. Back to Mail Online.

Links: PDF - Abstract

Code :


Keywords : method - experimental - segmentation - semantic - images -

Leave a Reply

Your email address will not be published. Required fields are marked *


Enjoy this blog? Please spread the word :)