mlsanityData to 14 Oct 2026

A Survey on Open-Set Image Recognition

arXiv 2312.15571 ↗First posted 25 Dec 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Open-set image recognition (OSR) aims to both classify known-class samples and identify unknown-class samples in the testing set, which supports robust classifiers in many realistic applications, such as autonomous driving, medical diagnosis, security monitoring, etc. In recent years, open-set recognition methods have achieved more and more attention, since it is usually difficult to obtain holistic information about the open world for model training. In this paper, we aim to summarize the up-to-date development of recent OSR methods, considering their rapid development in recent two or three years. Specifically, we firstly introduce a new taxonomy, under which we comprehensively review the existing DNN-based OSR methods. Then, we compare the performances of some typical and state-of-the-art OSR methods on both coarse-grained datasets and fine-grained datasets under both standard-dataset setting and cross-dataset setting, and further give the analysis of the comparison. Finally, we discuss some open issues and possible future directions in this community.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 101 of its 154 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

101 of 154 references.

References · 101

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  9. 2016Densely Connected Convolutional Networkscited by 6,720
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  11. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  12. 2021Zero-Shot Text-to-Image Generationcited by 4,288
38 more
  1. 2014Going Deeper with Convolutionscited by 4,241
  2. 2016Wide Residual Networkscited by 3,070
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  5. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  7. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  12. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  13. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  14. 2023A Survey on Multimodal Large Language Modelscited by 909
  15. 2018Self-Attention Generative Adversarial Networkscited by 809
  16. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  17. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  18. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  19. 2021Transformer in Transformercited by 633
  20. 2015Towards Open Set Deep Networkscited by 538
  21. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  22. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  23. 2018Invertible Residual Networkscited by 365
  24. 2015Adversarial Autoencoderscited by 364
  25. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  26. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  27. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  28. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 267
  29. 2014Towards Open World Recognitioncited by 226
  30. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  31. 2022Generalized Category Discoverycited by 211
  32. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  33. 2018Reducing Network Agnostophobiacited by 165
  34. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  35. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  36. 2023Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learnerscited by 152
  37. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  38. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146

50 most cited of 101 All 101 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  2. 2025Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learningcited by 6
  3. 2025DynaSubVAE: Adaptive Subgrouping for Scalable and Robust OOD Detectioncited by 0
  4. 2025The Finer the Better: Towards Granular-aware Open-set Domain Generalizationcited by 0
  5. 2026ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circlescited by 0
  6. 2026Beyond the Simplex: Balanced Prototype Geometry for Scorer-Agnostic Open-Set Recognitioncited by 0
  7. 2026Subject-Level Unknown-Identity Identification from Leap Motion Controller 2 Hand Landmarkscited by 0