@inproceedings{Ding_CVPR2022,
TITLE = {Decoupling Zero-Shot Semantic Segmentation},
AUTHOR = {Ding, Jian and Xue, Nan and Xia, Gui-Song and Dai, Dengxin},
LANGUAGE = {eng},
ISBN = {978-1-6654-6946-3},
DOI = {10.1109/CVPR52688.2022.01129},
PUBLISHER = {IEEE},
YEAR = {2022},
ABSTRACT = {Zero-shot semantic segmentation (ZS3) aims to segment the novel categories<br>that have not been seen in the training. Existing works formulate ZS3 as a<br>pixel-level zero-shot classification problem, and transfer semantic knowledge<br>from seen classes to unseen ones with the help of language models pre-trained<br>only with texts. While simple, the pixel-level ZS3 formulation shows the<br>limited capability to integrate vision-language models that are often<br>pre-trained with image-text pairs and currently demonstrate great potential for<br>vision tasks. Inspired by the observation that humans often perform<br>segment-level semantic labeling, we propose to decouple the ZS3 into two<br>sub-tasks: 1) a class-agnostic grouping task to group the pixels into segments.<br>2) a zero-shot classification task on segments. The former sub-task does not<br>involve category information and can be directly transferred to group pixels<br>for unseen classes. The latter subtask performs at segment-level and provides a<br>natural way to leverage large-scale vision-language models pre-trained with<br>image-text pairs (e.g. CLIP) for ZS3. Based on the decoupling formulation, we<br>propose a simple and effective zero-shot semantic segmentation model, called<br>ZegFormer, which outperforms the previous methods on ZS3 standard benchmarks by<br>large margins, e.g., 35 points on the PASCAL VOC and 3 points on the COCO-Stuff<br>in terms of mIoU for unseen classes. Code will be released at<br>https://github.com/dingjiansw101/ZegFormer.<br>},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)},
PAGES = {11573--11582},
ADDRESS = {New Orleans, LA, USA},
}