A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods. Another line of methods also cares about the performance of base classes in addition to the novel ones and thus establishes the incremental FSL scenario. In this paper, we generalize the above two under a more realistic yet complex setting, named by Semi-Supervised Incremental Few-Shot Learning (S2 I-FSL). To tackle the task, we propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data. Extensive experiments on standard FSL, semi-supervised FSL, incremental FSL, and the firstly built S2 I-FSL benchmarks demonstrate the effectiveness of our proposed method.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 43 of its 48 references that are in the map. First posted on arXiv 21 Oct 2021.
Builds on
43 of 48 references.
References · 43
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2019A Closer Look at Few-shot Classificationcited by 684
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
31 more
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2018How to train your MAMLcited by 309
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2020Few-Shot Class-Incremental Learningcited by 251
- 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
- 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
- 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
- 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
- 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
- 2019Prototype Rectification for Few-Shot Learningcited by 97
- 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
- 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
- 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 80
- 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
- 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 74
- 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
- 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 66
- 2021Few-Shot Lifelong Learningcited by 59
- 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
- 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
- 2020Transductive Information Maximization For Few-Shot Learningcited by 45
- 2019TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learningcited by 39
- 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
- 2020XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learningcited by 31
- 2020TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationcited by 30
- 2020How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learningcited by 16
- 2020PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learningcited by 9
- 2019Relational Generalized Few-Shot Learningcited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.