# Rethinking Semantic Segmentation: A Prototype View

arXiv: https://arxiv.org/abs/2203.15102 · HTML: https://mlsanity.com/paper/2203.15102/

## Key facts

- Cited by 140 papers in the map (data through 14 Oct 2026).
- Builds on 96 of its 146 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 30 of 96)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)

## Built on by (most cited first, 30 of 140)

- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization](https://mlsanity.com/paper/2210.04388/) (2022)
- [CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2310.16667/) (2023)
- [Learning with Mixture of Prototypes for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.02653/) (2024)
- [CORE: Cooperative Reconstruction for Multi-Agent Perception](https://mlsanity.com/paper/2307.11514/) (2023)
- [RGB-T Semantic Segmentation with Location, Activation, and Sharpening](https://mlsanity.com/paper/2210.14530/) (2022)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [Multi-Task Learning with Multi-Query Transformer for Dense Prediction](https://mlsanity.com/paper/2205.14354/) (2022)
- [CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation](https://mlsanity.com/paper/2307.15942/) (2023)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [PTaRL: Prototype-based Tabular Representation Learning via Space Calibration](https://mlsanity.com/paper/2407.05364/) (2024)
- [Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2310.19001/) (2023)
- [Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation](https://mlsanity.com/paper/2405.06228/) (2024)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [Hybrid Mamba for Few-Shot Segmentation](https://mlsanity.com/paper/2409.19613/) (2024)
- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [Eliminating Feature Ambiguity for Few-Shot Segmentation](https://mlsanity.com/paper/2407.09842/) (2024)
- [Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels](https://mlsanity.com/paper/2409.19846/) (2024)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [Spatial Structure Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11122/) (2024)
- [Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition](https://mlsanity.com/paper/2204.04654/) (2022)
- [Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview](https://mlsanity.com/paper/2211.08352/) (2022)
- [Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.07630/) (2024)
- [Visual Knowledge in the Big Model Era: Retrospect and Prospect](https://mlsanity.com/paper/2404.04308/) (2024)
- [COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation](https://mlsanity.com/paper/2210.01784/) (2022)
- [Towards Open-World Segmentation of Parts](https://mlsanity.com/paper/2305.16804/) (2023)

## Abstract (arXiv)

Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, this study uncovers several limitations of such parametric segmentation regime, and proposes a nonparametric alternative based on non-learnable prototypes. Instead of prior methods learning a single weight/query vector for each class in a fully parametric manner, our model represents each class as a set of non-learnable prototypes, relying solely on the mean features of several training pixels within that class. The dense prediction is thus achieved by nonparametric nearest prototype retrieving. This allows our model to directly shape the pixel embedding space, by optimizing the arrangement between embedded pixels and anchored prototypes. It is able to handle arbitrary number of classes with a constant amount of learnable parameters. We empirically show that, with FCN based and attention based segmentation models (i.e., HRNet, Swin, SegFormer) and backbones (i.e., ResNet, HRNet, Swin, MiT), our nonparametric framework yields compelling results over several datasets (i.e., ADE20K, Cityscapes, COCO-Stuff), and performs well in the large-vocabulary situation. We expect this work will provoke a rethink of the current de facto semantic segmentation model design.