Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy
Not on the map. Why?
Abstract (arXiv)
Unsupervised object discovery is commonly interpreted as the task of localizing and/or categorizing objects in visual data without the need for labeled examples. While current object recognition methods have proven highly effective for practical applications, the ongoing demand for annotated data in real-world scenarios drives research into unsupervised approaches. Furthermore, existing literature in object discovery is both extensive and diverse, posing a significant challenge for researchers that aim to navigate and synthesize this knowledge. Motivated by the evidenced interest in this avenue of research, and the lack of comprehensive studies that could facilitate a holistic understanding of unsupervised object discovery, this survey conducts an in-depth exploration of the existing approaches and systematically categorizes this compendium based on the tasks addressed and the families of techniques employed. Additionally, we present an overview of common datasets and metrics, highlighting the challenges of comparing methods due to varying evaluation protocols. This work intends to provide practitioners with an insightful perspective on the domain, with the hope of inspiring new ideas and fostering a deeper understanding of object discovery approaches.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 81 of its 150 references that are in the map. First posted on arXiv 30 Oct 2024.
Builds on
81 of 150 references.
References · 81
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
- 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
- 2020Object-Centric Learning with Slot Attentioncited by 876
- 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
- 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
- 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
- 2020Open-Vocabulary Object Detection Using Captionscited by 427
- 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
- 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
- 2020SCAN: Learning to Classify Images without Labelscited by 352
38 more
- 2020On the Binding Problem in Artificial Neural Networkscited by 233
- 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
- 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
- 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
- 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
- 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
- 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
- 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
- 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
- 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
- 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
- 2023Towards Open Vocabulary Learning: A Surveycited by 166
- 2019Salient Object Detection in the Deep Learning Era: An In-Depth Surveycited by 164
- 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
- 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
- 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
- 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
- 2017Neural Expectation Maximizationcited by 123
- 2019Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscited by 117
- 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
- 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
- 2021Unsupervised Discovery of Object Radiance Fieldscited by 101
- 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
- 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
- 2019Stacked Capsule Autoencoderscited by 82
- 2022Object discovery and representation networkscited by 80
- 2019Unsupervised Object Segmentation by Redrawingcited by 74
- 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
- 2016Tagger: Deep Unsupervised Perceptual Groupingcited by 69
- 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
- 2018Deep Feature Factorization For Concept Discoverycited by 64
- 2018FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discoverycited by 58
- 2020Generative Neurosymbolic Machinescited by 57
- 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
- 2018ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stackingcited by 55
- 2020A survey on Semi-, Self- and Unsupervised Learning for Image Classificationcited by 55
- 2021Large-Scale Unsupervised Object Discoverycited by 54
- 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
50 most cited of 81 All 81 (JSON)
Built on by
Citing papers per year: 2025: 2; 2026: 2.
4 papers.