# Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition

arXiv: https://arxiv.org/abs/2408.13373 · HTML: https://mlsanity.com/paper/2408.13373/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 28 of 28)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Task-Agnostic Meta-Learning for Few-shot Learning](https://mlsanity.com/paper/1805.07722/) (2018)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Learning Open Set Network with Discriminative Reciprocal Points](https://mlsanity.com/paper/2011.00178/) (2020)
- [Hybrid Models for Open Set Recognition](https://mlsanity.com/paper/2003.12506/) (2020)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning](https://mlsanity.com/paper/1910.02224/) (2019)
- [Memory Matching Networks for One-Shot Image Recognition](https://mlsanity.com/paper/1804.08281/) (2018)
- [Few-Shot Object Detection with Fully Cross-Transformer](https://mlsanity.com/paper/2203.15021/) (2022)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Few-Shot Open-Set Recognition using Meta-Learning](https://mlsanity.com/paper/2005.13713/) (2020)
- [Few-shot Open-set Recognition by Transformation Consistency](https://mlsanity.com/paper/2103.01537/) (2021)
- [Cooperative Bi-path Metric for Few-shot Learning](https://mlsanity.com/paper/2008.04031/) (2020)
- [Annotation-Efficient Untrimmed Video Action Recognition](https://mlsanity.com/paper/2011.14478/) (2020)
- [Few-shot Open-set Recognition Using Background as Unknowns](https://mlsanity.com/paper/2207.09059/) (2022)
- [Adaptive Discovering and Merging for Incremental Novel Class Discovery](https://mlsanity.com/paper/2403.03382/) (2024)

## Built on by (most cited first, 6 of 6)

- [Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05235/) (2026)
- [Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection](https://mlsanity.com/paper/2510.00303/) (2025)
- [Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment](https://mlsanity.com/paper/2603.17655/) (2026)
- [When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network](https://mlsanity.com/paper/2506.17457/) (2025)
- [Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2603.18541/) (2026)
- [Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2605.25799/) (2026)

## Abstract (arXiv)

Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data. Existing approaches, particularly Negative-Prototype-Based methods, generate negative prototypes based solely on known class data. However, as the unknown space is infinite while the known space is limited, these methods suffer from limited representation capability. To address this limitation, we propose a novel approach, termed Diversified Negative Prototypes Generator (DNPG), which adopts the principle of "learning unknowns from unknowns." Our method leverages the unknown space information learned from base classes to generate more representative negative prototypes for novel classes. During the pre-training phase, we learn the unknown space representation of the base classes. This representation, along with inter-class relationships, is then utilized in the meta-learning process to construct negative prototypes for novel classes. To prevent prototype collapse and ensure adaptability to varying data compositions, we introduce the Swap Alignment (SA) module. Our DNPG model, by learning from the unknown space, generates negative prototypes that cover a broader unknown space, thereby achieving state-of-the-art performance on three standard FSOR datasets.