mlsanityData to 14 Oct 2026

PartImageNet: A Large, High-Quality Dataset of Parts

arXiv 2112.00933 ↗First posted 2 Dec 2021cs.CVcited by 107

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

It is natural to represent objects in terms of their parts. This has the potential to improve the performance of algorithms for object recognition and segmentation but can also help for downstream tasks like activity recognition. Research on part-based models, however, is hindered by the lack of datasets with per-pixel part annotations. This is partly due to the difficulty and high cost of annotating object parts so it has rarely been done except for humans (where there exists a big literature on part-based models). To help address this problem, we propose PartImageNet, a large, high-quality dataset with part segmentation annotations. It consists of 158 classes from ImageNet with approximately 24,000 images. PartImageNet is unique because it offers part-level annotations on a general set of classes including non-rigid, articulated objects, while having an order of magnitude larger size compared to existing part datasets (excluding datasets of humans). It can be utilized for many vision tasks including Object Segmentation, Semantic Part Segmentation, Few-shot Learning and Part Discovery. We conduct comprehensive experiments which study these tasks and set up a set of baselines. The dataset and scripts are released at https://github.com/TACJu/PartImageNet.

Key facts. Cited by 107 papers in the map (data through 14 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

36 of 64 references.

References · 36

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  10. 2019Panoptic Feature Pyramid Networkscited by 645
  11. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  12. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
24 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  3. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
  4. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  5. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  6. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  7. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  8. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  9. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  10. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  11. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  12. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  13. 2017Unsupervised learning of object landmarks by factorized spatial embeddingscited by 64
  14. 2018Deep Feature Factorization For Concept Discoverycited by 64
  15. 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
  16. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  17. 2021Part-aware Panoptic Segmentationcited by 56
  18. 2020DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learningcited by 49
  19. 2017Joint Multi-Person Pose Estimation and Semantic Part Segmentationcited by 41
  20. 2014Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relationscited by 24
  21. 2015Joint Object and Part Segmentation using Deep Learned Potentialscited by 23
  22. 2021FAPIS: A Few-shot Anchor-free Part-based Instance Segmentercited by 15
  23. 2015Unsupervised learning of object semantic parts from internal states of CNNs by population encodingcited by 8
  24. 2020Unsupervised Part Discovery by Unsupervised Disentanglementcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 11; 2023: 16; 2024: 32; 2025: 34; 2026: 14.

107 papers.

Sort:

By area:

  1. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  2. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 267
  3. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 239
  4. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  5. 2023Osprey: Pixel Understanding with Visual Instruction Tuningcited by 159
  6. 2023PACO: Parts and Attributes of Common Objectscited by 146
  7. 2022Dataset Pruning: Reducing Training Data by Examining Generalization Influencecited by 133
  8. 2022SemMAE: Semantic-Guided Masking for Learning Masked Autoencoderscited by 114
  9. 2025Detect Anything via Next Point Predictioncited by 73
  10. 2024SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentationcited by 69
  11. 2024EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Modelcited by 65
  12. 2024Visual Agents as Fast and Slow Thinkerscited by 53
38 more
  1. 2023Going Denser with Open-Vocabulary Part Segmentationcited by 51
  2. 2022Teaching Matters: Investigating the Role of Supervision in Vision Transformerscited by 45
  3. 2023Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shapecited by 44
  4. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  5. 2023Tracking with Human-Intent Reasoningcited by 33
  6. 2024DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perceptioncited by 32
  7. 2023Universal Segmentation at Arbitrary Granularity with Language Instructioncited by 29
  8. 2024Segment Anything without Supervisioncited by 28
  9. 2025MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentationcited by 28
  10. 2023Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentationcited by 22
  11. 2023PDiscoNet: Semantically consistent part discovery for fine-grained recognitioncited by 21
  12. 2024Subobject-level Image Tokenizationcited by 21
  13. 2025PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularitycited by 21
  14. 2025HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Modelcited by 20
  15. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  16. 2022Learning Hierarchical Image Segmentation For Recognition and By Recognitioncited by 16
  17. 2024DCBM: Data-Efficient Visual Concept Bottleneck Modelscited by 16
  18. 2023Towards Open-World Segmentation of Partscited by 15
  19. 2024PartGLEE: A Foundation Model for Recognizing and Parsing Any Objectscited by 15
  20. 2024USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentationcited by 14
  21. 2024DEAL: Disentangle and Localize Concept-level Explanations for VLMscited by 14
  22. 2024GraCo: Granularity-Controllable Interactive Segmentationcited by 13
  23. 2023From Posterior Sampling to Meaningful Diversity in Image Restorationcited by 12
  24. 2025Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Modelscited by 12
  25. 2022Part-Based Models Improve Adversarial Robustnesscited by 11
  26. 2023Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentationcited by 11
  27. 2025GroundingSuite: Measuring Complex Multi-Granular Pixel Groundingcited by 11
  28. 2022Visual Recognition by Requestcited by 10
  29. 20243x2: 3D Object Part Segmentation by 2D Semantic Correspondencescited by 10
  30. 2024PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformerscited by 9
  31. 20252HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videoscited by 9
  32. 2023Towards Open-Ended Visual Recognition with Large Language Modelcited by 8
  33. 2025Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosiscited by 8
  34. 2023Structural Information Guided Multimodal Pre-training for Vehicle-centric Perceptioncited by 7
  35. 2024LLMBind: A Unified Modality-Task Integration Frameworkcited by 7
  36. 2024PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneckcited by 7
  37. 2024PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognitioncited by 7
  38. 2025PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Modelscited by 7

50 most cited of 107 All 107 (JSON)