Task-Adaptive Negative Envision for Few-Shot Open-Set Recognition
Not on the map. Why?
Abstract (arXiv)
We study the problem of few-shot open-set recognition (FSOR), which learns a recognition system capable of both fast adaptation to new classes with limited labeled examples and rejection of unknown negative samples. Traditional large-scale open-set methods have been shown ineffective for FSOR problem due to data limitation. Current FSOR methods typically calibrate few-shot closed-set classifiers to be sensitive to negative samples so that they can be rejected via thresholding. However, threshold tuning is a challenging process as different FSOR tasks may require different rejection powers. In this paper, we instead propose task-adaptive negative class envision for FSOR to integrate threshold tuning into the learning process. Specifically, we augment the few-shot closed-set classifier with additional negative prototypes generated from few-shot examples. By incorporating few-shot class correlations in the negative generation process, we are able to learn dynamic rejection boundaries for FSOR tasks. Besides, we extend our method to generalized few-shot open-set recognition (GFSOR), which requires classification on both many-shot and few-shot classes as well as rejection of negative samples. Extensive experiments on public benchmarks validate our methods on both problems.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 2; 2023: 4; 2024: 5; 2025: 0; 2026: 3.
14 papers.
Sort:
By area:
- 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
- 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
- 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
- 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
- 2024Enhancing Vision-Language Few-Shot Adaptation with Negative Learningcited by 8
- 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
- 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
- 2024HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adaptercited by 3
- 2023FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?cited by 2
- 2026Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypescited by 2
- 2024LLM meets Vision-Language Models for Zero-Shot One-Class Classificationcited by 1
- 2024Unlocking Transfer Learning for Open-World Few-Shot Recognitioncited by 0
- 2026Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement29 Jul 2026
- 2026Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes1 Jul 2026
- 2026A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination4 Mar 2026
- 2024Unlocking Transfer Learning for Open-World Few-Shot Recognition15 Nov 2024
- 2024HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter10 Oct 2024
- 2024Towards Few-Shot Learning in the Open World: A Review and Beyond19 Aug 2024
- 2024LLM meets Vision-Language Models for Zero-Shot One-Class Classification31 Mar 2024
- 2024Enhancing Vision-Language Few-Shot Adaptation with Negative Learning19 Mar 2024
- 2023FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?9 Jul 2023
- 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognition24 Apr 2023
- 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection16 Mar 2023
- 2023Open-Set Likelihood Maximization for Few-Shot Learning20 Jan 2023
- 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
- 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
- 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
- 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
- 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
- 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
- 2023FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?cited by 2
- 2026Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypescited by 2
- 2024Unlocking Transfer Learning for Open-World Few-Shot Recognitioncited by 0
- 2026A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discriminationcited by 0
- 2026Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancementcited by 0
- 2026Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement29 Jul 2026
- 2026Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes1 Jul 2026
- 2026A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination4 Mar 2026
- 2024Unlocking Transfer Learning for Open-World Few-Shot Recognition15 Nov 2024
- 2024Towards Few-Shot Learning in the Open World: A Review and Beyond19 Aug 2024
- 2023FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?9 Jul 2023
- 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognition24 Apr 2023
- 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection16 Mar 2023
- 2023Open-Set Likelihood Maximization for Few-Shot Learning20 Jan 2023
- 2022Towards Generalized Few-Shot Open-Set Object Detection28 Oct 2022
- 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detection26 Sep 2022