# E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

arXiv: https://arxiv.org/abs/2203.04074 · HTML: https://mlsanity.com/paper/2203.04074/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 38 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 30 of 33)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [SOLO: Segmenting Objects by Locations](https://mlsanity.com/paper/1912.04488/) (2019)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Boundary IoU: Improving Object-Centric Image Segmentation Evaluation](https://mlsanity.com/paper/2103.16562/) (2021)
- [UPSNet: A Unified Panoptic Segmentation Network](https://mlsanity.com/paper/1901.03784/) (2019)
- [BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation](https://mlsanity.com/paper/2001.00309/) (2020)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++](https://mlsanity.com/paper/1803.09693/) (2018)
- [Deep Snake for Real-Time Instance Segmentation](https://mlsanity.com/paper/2001.01629/) (2020)
- [TensorMask: A Foundation for Dense Object Segmentation](https://mlsanity.com/paper/1903.12174/) (2019)
- [Fast Interactive Object Annotation with Curve-GCN](https://mlsanity.com/paper/1903.06874/) (2019)
- [PolyTransform: Deep Polygon Transformer for Instance Segmentation](https://mlsanity.com/paper/1912.02801/) (2019)
- [Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth](https://mlsanity.com/paper/1906.11109/) (2019)
- [SSAP: Single-Shot Instance Segmentation With Affinity Pyramid](https://mlsanity.com/paper/1909.01616/) (2019)
- [Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation](https://mlsanity.com/paper/1804.08864/) (2018)
- [Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation](https://mlsanity.com/paper/2007.02846/) (2020)
- [Amodal Segmentation Based on Visible Region Segmentation and Shape Prior](https://mlsanity.com/paper/2012.05598/) (2020)
- [Explicit Shape Encoding for Real-Time Instance Segmentation](https://mlsanity.com/paper/1908.04067/) (2019)
- [Hierarchical Recurrent Attention Networks for Structured Online Maps](https://mlsanity.com/paper/2012.12314/) (2020)
- [PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond](https://mlsanity.com/paper/2105.02184/) (2021)
- [Affinity Derivation and Graph Merge for Instance Segmentation](https://mlsanity.com/paper/1811.10870/) (2018)
- [Dense RepPoints: Representing Visual Objects with Dense Point Sets](https://mlsanity.com/paper/1912.11473/) (2019)

## Built on by (most cited first, 27 of 27)

- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [CTVIS: Consistent Training for Online Video Instance Segmentation](https://mlsanity.com/paper/2307.12616/) (2023)
- [FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation](https://mlsanity.com/paper/2303.08594/) (2023)
- [Sign Language Translation with Iterative Prototype](https://mlsanity.com/paper/2308.12191/) (2023)
- [BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction](https://mlsanity.com/paper/2211.03373/) (2022)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [Recurrent Generic Contour-based Instance Segmentation with Progressive Learning](https://mlsanity.com/paper/2301.08898/) (2023)
- [Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery](https://mlsanity.com/paper/2412.07899/) (2024)
- [P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Images](https://mlsanity.com/paper/2406.02930/) (2024)
- [BARS: A Benchmark for Airport Runway Segmentation](https://mlsanity.com/paper/2210.12922/) (2022)
- [PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions](https://mlsanity.com/paper/2307.14070/) (2023)
- [HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery](https://mlsanity.com/paper/2507.16251/) (2025)
- [VectorLLM: Human-like Extraction of Structured Building Contours vis Multimodal LLMs](https://mlsanity.com/paper/2507.04664/) (2025)
- [Growing Instance Mask on Leaf](https://mlsanity.com/paper/2211.16738/) (2022)
- [What You See Is What You Detect: Towards better Object Densification in 3D detection](https://mlsanity.com/paper/2310.17842/) (2023)
- [Multimodal Urban Areas of Interest Generation via Remote Sensing Imagery and Geographical Prior](https://mlsanity.com/paper/2401.06550/) (2024)
- [ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer](https://mlsanity.com/paper/2501.17688/) (2025)
- [UniVector: Unified Vector Extraction via Instance-Geometry Interaction](https://mlsanity.com/paper/2510.13234/) (2025)
- [Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2303.15737/) (2023)
- [Synthetic Instance Segmentation from Semantic Image Segmentation Masks](https://mlsanity.com/paper/2308.00949/) (2023)
- [Bayesian Fusion of Active Contour Models and ConvNet Priors for Standing Dead Tree Segmentation](https://mlsanity.com/paper/2410.07421/) (2024)
- [Occlusion-Ordered Semantic Instance Segmentation](https://mlsanity.com/paper/2504.14054/) (2025)
- [Walk the Lines 2: Contour Tracking for Detailed Segmentation](https://mlsanity.com/paper/2511.05210/) (2025)
- [Bridging Object Detection and Segmentation with Polygon Detection Transformers](https://mlsanity.com/paper/2603.09245/) (2026)
- [PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images](https://mlsanity.com/paper/2606.08920/) (2026)
- [ODE-Based Transformer Decoders for Iterative Sign Language Translation](https://mlsanity.com/paper/2608.11352/) (2026)
- [Topologically Consistent Agricultural Parcel Vectorization with Semantic-Guided Diffusion and Topology-Aware Polygonization](https://mlsanity.com/paper/2609.07520/) (2026)

## Abstract (arXiv)

Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of hand-crafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512*512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.