# Few-shot Open-set Recognition by Transformation Consistency

arXiv: https://arxiv.org/abs/2103.01537 · HTML: https://mlsanity.com/paper/2103.01537/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020)
- [Finding Task-Relevant Features for Few-Shot Learning by Category Traversal](https://mlsanity.com/paper/1905.11116/) (2019)
- [Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks](https://mlsanity.com/paper/1805.07925/) (2018)
- [TaskNorm: Rethinking Batch Normalization for Meta-Learning](https://mlsanity.com/paper/2003.03284/) (2020)
- [Few-Shot Open-Set Recognition using Meta-Learning](https://mlsanity.com/paper/2005.13713/) (2020)
- [Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation](https://mlsanity.com/paper/2007.07867/) (2020)

## Built on by (most cited first, 29 of 29)

- [Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning](https://mlsanity.com/paper/2110.09446/) (2021)
- [Open-Set Likelihood Maximization for Few-Shot Learning](https://mlsanity.com/paper/2301.08390/) (2023)
- [Glocal Energy-based Learning for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2304.11855/) (2023)
- [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://mlsanity.com/paper/2208.00183/) (2022)
- [Towards Generalized Few-Shot Open-Set Object Detection](https://mlsanity.com/paper/2210.15996/) (2022)
- [Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting](https://mlsanity.com/paper/2206.13691/) (2022)
- [A Survey on Open-Set Image Recognition](https://mlsanity.com/paper/2312.15571/) (2023)
- [Few-shot Open-set Recognition Using Background as Unknowns](https://mlsanity.com/paper/2207.09059/) (2022)
- [Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2408.13373/) (2024)
- [Towards Few-Shot Learning in the Open World: A Review and Beyond](https://mlsanity.com/paper/2408.09722/) (2024)
- [Anticipating the Unseen Discrepancy for Vision and Language Navigation](https://mlsanity.com/paper/2209.04725/) (2022)
- [Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons](https://mlsanity.com/paper/2301.03118/) (2023)
- [Domain Adaptive Few-Shot Open-Set Learning](https://mlsanity.com/paper/2309.12814/) (2023)
- [Reconstruction guided Meta-learning for Few Shot Open Set Recognition](https://mlsanity.com/paper/2108.00340/) (2021)
- [A Survey of Deep Visual Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2303.09253/) (2023)
- [Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary](https://mlsanity.com/paper/2406.18443/) (2024)
- [ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification](https://mlsanity.com/paper/2507.11845/) (2025)
- [Model-Agnostic Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2206.09236/) (2022)
- [EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits](https://mlsanity.com/paper/2408.02052/) (2024)
- [Hyperbolic Dual Feature Augmentation for Open-Environment](https://mlsanity.com/paper/2506.08906/) (2025)
- [A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution](https://mlsanity.com/paper/2305.05079/) (2023)
- [Advancing Image Retrieval with Few-Shot Learning and Relevance Feedback](https://mlsanity.com/paper/2312.11078/) (2023)
- [LLM meets Vision-Language Models for Zero-Shot One-Class Classification](https://mlsanity.com/paper/2404.00675/) (2024)
- [Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement](https://mlsanity.com/paper/2506.16728/) (2025)
- [Accessible Instruction-Following Agent](https://mlsanity.com/paper/2305.06358/) (2023)
- [Unlocking Transfer Learning for Open-World Few-Shot Recognition](https://mlsanity.com/paper/2411.09986/) (2024)
- [Few-shot Novel Category Discovery](https://mlsanity.com/paper/2505.08260/) (2025)
- [OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection](https://mlsanity.com/paper/2601.22685/) (2026)
- [A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination](https://mlsanity.com/paper/2603.04125/) (2026)

## 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.