# PolyFormer: Referring Image Segmentation as Sequential Polygon Generation

arXiv: https://arxiv.org/abs/2302.07387 · HTML: https://mlsanity.com/paper/2302.07387/

## Key facts

- Cited by 148 papers in the map (data through 14 Oct 2026).
- Builds on 77 of its 95 references that are in the map.
- First posted on arXiv 14 Feb 2023.

## Builds on (most cited first, 30 of 77)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)

## Built on by (most cited first, 30 of 148)

- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [PaLI-3 Vision Language Models: Smaller, Faster, Stronger](https://mlsanity.com/paper/2310.09199/) (2023)
- [LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models](https://mlsanity.com/paper/2312.02949/) (2023)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [General Object Foundation Model for Images and Videos at Scale](https://mlsanity.com/paper/2312.09158/) (2023)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation](https://mlsanity.com/paper/2409.10542/) (2024)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [Zero-shot Referring Image Segmentation with Global-Local Context Features](https://mlsanity.com/paper/2303.17811/) (2023)
- [RRSIS: Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2306.08625/) (2023)
- [SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation](https://mlsanity.com/paper/2305.17011/) (2023)
- [Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation](https://mlsanity.com/paper/2404.03645/) (2024)
- [LaSagnA: Language-based Segmentation Assistant for Complex Queries](https://mlsanity.com/paper/2404.08506/) (2024)
- [Hierarchical Open-vocabulary Universal Image Segmentation](https://mlsanity.com/paper/2307.00764/) (2023)
- [Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model](https://mlsanity.com/paper/2312.12423/) (2023)
- [Toward Visual Grounding: A Survey](https://mlsanity.com/paper/2412.20206/) (2024)
- [LLaFS: When Large Language Models Meet Few-Shot Segmentation](https://mlsanity.com/paper/2311.16926/) (2023)
- [Described Object Detection: Liberating Object Detection with Flexible Expressions](https://mlsanity.com/paper/2307.12813/) (2023)
- [Mask Grounding for Referring Image Segmentation](https://mlsanity.com/paper/2312.12198/) (2023)
- [Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception](https://mlsanity.com/paper/2403.02969/) (2024)
- [ReMamber: Referring Image Segmentation with Mamba Twister](https://mlsanity.com/paper/2403.17839/) (2024)
- [SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion](https://mlsanity.com/paper/2409.17531/) (2024)
- [LocCa: Visual Pretraining with Location-aware Captioners](https://mlsanity.com/paper/2403.19596/) (2024)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation](https://mlsanity.com/paper/2512.10945/) (2025)
- [Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models](https://mlsanity.com/paper/2308.16777/) (2023)
- [HyperSeg: Towards Universal Visual Segmentation with Large Language Model](https://mlsanity.com/paper/2411.17606/) (2024)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)

## Abstract (arXiv)

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.