mlsanityData to 7 Oct 2026

Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation

arXiv 2211.14513 ↗First posted 26 Nov 2022cs.CV cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Unsupervised image semantic segmentation(UISS) aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS and image-wise representation learning. Based on the analysis, we argue that the existing MI-based methods in UISS suffer from representation collapse. By this, we proposed a robust network called Semantic Attention Network(SAN), in which a new module Semantic Attention(SEAT) is proposed to generate pixel-wise and semantic features dynamically. Experimental results on multiple semantic segmentation benchmarks show that our unsupervised segmentation framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 26 Nov 2022.

Builds on

29 of 42 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2017Mask R-CNNcited by 7,259
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  11. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  12. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
17 more
  1. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  2. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  3. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  4. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  5. 2016Colorful Image Colorizationcited by 1,113
  6. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  7. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  8. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  9. 2021Intriguing Properties of Vision Transformerscited by 446
  10. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  11. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  12. 2019SegSort: Segmentation by Discriminative Sorting of Segmentscited by 96
  13. 2020Autoregressive Unsupervised Image Segmentationcited by 60
  14. 2021TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentationcited by 38
  15. 2021Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularizationcited by 13
  16. 2021InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximizationcited by 11
  17. 2022Fully Self-Supervised Learning for Semantic Segmentationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 0; 2025: 1; 2026: 1.

10 papers.

  1. 2023Video Understanding with Large Language Models: A Surveycited by 203
  2. 2023Feature Alignment and Uniformity for Test Time Adaptationcited by 42
  3. 2023Prototype Knowledge Distillation for Medical Segmentation with Missing Modalitycited by 24
  4. 2023Object-centric Learning with Cyclic Walks between Parts and Wholecited by 16
  5. 2023Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevancecited by 10
  6. 2023Cross Contrasting Feature Perturbation for Domain Generalizationcited by 9
  7. 2025Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitivescited by 2
  8. 2023Bootstrap The Original Latent: Learning a Private Model from a Black-box Modelcited by 1
  9. 2023Repurposing SAM for User-Defined Semantics Aware Segmentationcited by 0
  10. 2026ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margincited by 0