Better Generalized Few-Shot Learning Even Without Base Data
Not on the map. Why?
Abstract (arXiv)
This paper introduces and studies zero-base generalized few-shot learning (zero-base GFSL), which is an extreme yet practical version of few-shot learning problem. Motivated by the cases where base data is not available due to privacy or ethical issues, the goal of zero-base GFSL is to newly incorporate the knowledge of few samples of novel classes into a pretrained model without any samples of base classes. According to our analysis, we discover the fact that both mean and variance of the weight distribution of novel classes are not properly established, compared to those of base classes. The existing GFSL methods attempt to make the weight norms balanced, which we find helps only the variance part, but discard the importance of mean of weights particularly for novel classes, leading to the limited performance in the GFSL problem even with base data. In this paper, we overcome this limitation by proposing a simple yet effective normalization method that can effectively control both mean and variance of the weight distribution of novel classes without using any base samples and thereby achieve a satisfactory performance on both novel and base classes. Our experimental results somewhat surprisingly show that the proposed zero-base GFSL method that does not utilize any base samples even outperforms the existing GFSL methods that make the best use of base data. Our implementation is available at: https://github.com/bigdata-inha/Zero-Base-GFSL.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 29 Nov 2022.
Builds on
36 of 53 references.
References · 36
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 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
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
- 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
- 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
- 2019A Closer Look at Few-shot Classificationcited by 684
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
24 more
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 283
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
- 2018DropBlock: A regularization method for convolutional networkscited by 262
- 2020Few-Shot Class-Incremental Learningcited by 251
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
- 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
- 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
- 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
- 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
- 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
- 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
- 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 66
- 2021Few-Shot Lifelong Learningcited by 59
- 2017Learning Robust Visual-Semantic Embeddingscited by 56
- 2019Few-Shot Learning with Global Class Representationscited by 44
- 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
- 2019Relational Generalized Few-Shot Learningcited by 6
Built on by
Citing papers per year: 2023: 2; 2024: 1.
3 papers.