mlsanityData to 7 Oct 2026

Few-shot Open-set Recognition by Transformation Consistency

arXiv 2103.01537 ↗First posted 2 Mar 2021cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

In this paper, we attack a few-shot open-set recognition (FSOSR) problem, which is a combination of few-shot learning (FSL) and open-set recognition (OSR). It aims to quickly adapt a model to a given small set of labeled samples while rejecting unseen class samples. Since OSR requires rich data and FSL considers closed-set classification, existing OSR and FSL methods show poor performances in solving FSOSR problems. The previous FSOSR method follows the pseudo-unseen class sample-based methods, which collect pseudo-unseen samples from the other dataset or synthesize samples to model unseen class representations. However, this approach is heavily dependent on the composition of the pseudo samples. In this paper, we propose a novel unknown class sample detector, named SnaTCHer, that does not require pseudo-unseen samples. Based on the transformation consistency, our method measures the difference between the transformed prototypes and a modified prototype set. The modified set is composed by replacing a query feature and its predicted class prototype. SnaTCHer rejects samples with large differences to the transformed prototypes. Our method alters the unseen class distribution estimation problem to a relative feature transformation problem, independent of pseudo-unseen class samples. We investigate our SnaTCHer with various prototype transformation methods and observe that our method consistently improves unseen class sample detection performance without closed-set classification reduction.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

30 of 39 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Layer Normalizationcited by 5,579
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2017Deep Setscited by 1,394
  12. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
18 more
  1. 2015Towards Open Set Deep Networkscited by 533
  2. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  3. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  4. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  5. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  6. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  7. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  8. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  9. 2018Reducing Network Agnostophobiacited by 165
  10. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  11. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  12. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  13. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  14. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  15. 2018Batch-Instance Normalization for Adaptively Style-Invariant Neural Networkscited by 77
  16. 2020TaskNorm: Rethinking Batch Normalization for Meta-Learningcited by 50
  17. 2020Few-Shot Open-Set Recognition using Meta-Learningcited by 50
  18. 2020Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translationcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 9; 2024: 6; 2025: 4; 2026: 2.

29 papers.

Sort:

By area:

  1. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  2. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  3. 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
  4. 2022Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Networkcited by 9
  5. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
  6. 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
  7. 2023A Survey on Open-Set Image Recognitioncited by 7
  8. 2022Few-shot Open-set Recognition Using Background as Unknownscited by 6
  9. 2024Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognitioncited by 6
  10. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  11. 2022Anticipating the Unseen Discrepancy for Vision and Language Navigationcited by 4
  12. 2023Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Personscited by 4
17 more
  1. 2023Domain Adaptive Few-Shot Open-Set Learningcited by 4
  2. 2021Reconstruction guided Meta-learning for Few Shot Open Set Recognitioncited by 3
  3. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  4. 2024Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundarycited by 3
  5. 2025ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classificationcited by 3
  6. 2022Model-Agnostic Few-Shot Open-Set Recognitioncited by 2
  7. 2024EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logitscited by 2
  8. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
  9. 2023A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attributioncited by 1
  10. 2023Advancing Image Retrieval with Few-Shot Learning and Relevance Feedbackcited by 1
  11. 2024LLM meets Vision-Language Models for Zero-Shot One-Class Classificationcited by 1
  12. 2025Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancementcited by 1
  13. 2023Accessible Instruction-Following Agentcited by 0
  14. 2024Unlocking Transfer Learning for Open-World Few-Shot Recognitioncited by 0
  15. 2025Few-shot Novel Category Discoverycited by 0
  16. 2026OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detectioncited by 0
  17. 2026A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discriminationcited by 0