English

PolyFormer: Referring Image Segmentation as Sequential Polygon Generation

Computer Vision and Pattern Recognition 2023-03-29 v2

Abstract

In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coordinates directly, without any coordinate quantization error. In the experiments, PolyFormer outperforms the prior art by a clear margin, e.g., 5.40% and 4.52% absolute improvements on the challenging RefCOCO+ and RefCOCOg datasets. It also shows strong generalization ability when evaluated on the referring video segmentation task without fine-tuning, e.g., achieving competitive 61.5% J&F on the Ref-DAVIS17 dataset.

Keywords

Cite

@article{arxiv.2302.07387,
  title  = {PolyFormer: Referring Image Segmentation as Sequential Polygon Generation},
  author = {Jiang Liu and Hui Ding and Zhaowei Cai and Yuting Zhang and Ravi Kumar Satzoda and Vijay Mahadevan and R. Manmatha},
  journal= {arXiv preprint arXiv:2302.07387},
  year   = {2023}
}

Comments

CVPR 2023. Project Page: https://polyformer.github.io/

R2 v1 2026-06-28T08:40:20.225Z