Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy
Not on the map. Why?
Abstract (arXiv)
Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem. We found that the existing works often build their few-shot model based on the image-level feature by mixing all local-level features, which leads to the discriminative location bias and information loss in local details. To tackle the problem, this paper returns the perspective to the local-level feature and proposes a series of local-level strategies. Specifically, we present (a) a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, (b) a novel local-level similarity measure to capture the accurate comparison between local-level features, and (c) a local-level knowledge transfer that can synthesize different knowledge transfers from the base category according to different location features. Extensive experiments justify that our proposed local-level strategies can significantly boost the performance and achieve 2.8%-7.2% improvements over the baseline across different benchmark datasets, which also achieves state-of-the-art accuracy.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 20 references that are in the map. First posted on arXiv 8 Nov 2021.
Builds on
19 of 20 references.
References · 19
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
- 2013Network In Networkcited by 600
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2018Meta-learning with differentiable closed-form solverscited by 395
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
7 more
- 2019Cross Attention Network for Few-shot Classificationcited by 218
- 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
- 2020Empirical Bayes Transductive Meta-Learning with Synthetic Gradientscited by 48
- 2020Task Augmentation by Rotating for Meta-Learningcited by 18
- 2020Meta-Learned Confidence for Few-shot Learningcited by 9
- 2021Few-shot Image Classification with Multi-Facet Prototypescited by 3
Built on by
Citing papers per year: 2023: 2.
2 papers.