# Pixel Consensus Voting for Panoptic Segmentation

arXiv: https://arxiv.org/abs/2004.01849 · HTML: https://mlsanity.com/paper/2004.01849/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [Waymo Open Dataset: Panoramic Video Panoptic Segmentation](https://mlsanity.com/paper/2206.07704/) (2022)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain](https://mlsanity.com/paper/2306.04557/) (2023)
- [Panoptic Segmentation: A Review](https://mlsanity.com/paper/2111.10250/) (2021)
- [kMaX-DeepLab: k-means Mask Transformer](https://mlsanity.com/paper/2207.04044/) (2022)
- [LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network](https://mlsanity.com/paper/2203.07186/) (2022)
- [SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion](https://mlsanity.com/paper/2209.00381/) (2022)
- [CFNet: Learning Correlation Functions for One-Stage Panoptic Segmentation](https://mlsanity.com/paper/2201.04796/) (2022)
- [SUNet: Scale-aware Unified Network for Panoptic Segmentation](https://mlsanity.com/paper/2209.02877/) (2022)

## Abstract (arXiv)

The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the Generalized Hough transform. Pixels cast discretized, probabilistic votes for the likely regions that contain instance centroids. At the detected peaks that emerge in the voting heatmap, backprojection is applied to collect pixels and produce instance masks. Unlike a sliding window detector that densely enumerates object proposals, our method detects instances as a result of the consensus among pixel-wise votes. We implement vote aggregation and backprojection using native operators of a convolutional neural network. The discretization of centroid voting reduces the training of instance segmentation to pixel labeling, analogous and complementary to FCN-style semantic segmentation, leading to an efficient and unified architecture that jointly models things and stuff. We demonstrate the effectiveness of our pipeline on COCO and Cityscapes Panoptic Segmentation and obtain competitive results. Code will be open-sourced.