mlsanityData to 7 Oct 2026

Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation

arXiv 2306.07404 ↗First posted 12 Jun 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

In this work, we present a robust approach for joint part and object segmentation. Specifically, we reformulate object and part segmentation as an optimization problem and build a hierarchical feature representation including pixel, part, and object-level embeddings to solve it in a bottom-up clustering manner. Pixels are grouped into several clusters where the part-level embeddings serve as cluster centers. Afterwards, object masks are obtained by compositing the part proposals. This bottom-up interaction is shown to be effective in integrating information from lower semantic levels to higher semantic levels. Based on that, our novel approach Compositor produces part and object segmentation masks simultaneously while improving the mask quality. Compositor achieves state-of-the-art performance on PartImageNet and Pascal-Part by outperforming previous methods by around 0.9% and 1.3% on PartImageNet, 0.4% and 1.7% on Pascal-Part in terms of part and object mIoU and demonstrates better robustness against occlusion by around 4.4% and 7.1% on part and object respectively. Code will be available at https://github.com/TACJu/Compositor.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

36 of 54 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  12. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
24 more
  1. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  2. 2020Object-Centric Learning with Slot Attentioncited by 865
  3. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  4. 2019Panoptic Feature Pyramid Networkscited by 644
  5. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  6. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  7. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  8. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  9. 2021K-Net: Towards Unified Image Segmentationcited by 211
  10. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  11. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 107
  12. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  13. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  14. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  15. 2022CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentationcited by 60
  16. 2020Robust Object Detection under Occlusion with Context-Aware CompositionalNetscited by 54
  17. 2020Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusioncited by 47
  18. 2021NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimationcited by 41
  19. 2021Unsupervised Part Segmentation through Disentangling Appearance and Shapecited by 29
  20. 2021Simple Training Strategies and Model Scaling for Object Detectioncited by 25
  21. 2015Joint Object and Part Segmentation using Deep Learned Potentialscited by 23
  22. 2022Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Featurescited by 23
  23. 2020Attention-based Joint Detection of Object and Semantic Partcited by 11
  24. 2021CORL: Compositional Representation Learning for Few-Shot Classificationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 2; 2026: 1.

11 papers.

  1. 2024Visually Consistent Hierarchical Image Classificationcited by 16
  2. 2024PartGLEE: A Foundation Model for Recognizing and Parsing Any Objectscited by 15
  3. 2024PartCraft: Crafting Creative Objects by Partscited by 13
  4. 2024SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Imagescited by 5
  5. 2024WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Modelscited by 4
  6. 2025Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentationcited by 4
  7. 2026PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentationcited by 4
  8. 2024Understanding Multi-Granularity for Open-Vocabulary Part Segmentationcited by 3
  9. 2024From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregationcited by 0
  10. 2024OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsingcited by 0
  11. 2025Dictionary-based Framework for Interpretable and Consistent Object Parsingcited by 0