Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples
Not on the map. Why?
Abstract (arXiv)
Over the last couple of years few-shot learning (FSL) has attracted great attention towards minimizing the dependency on labeled training examples. An inherent difficulty in FSL is the handling of ambiguities resulting from having too few training samples per class. To tackle this fundamental challenge in FSL, we aim to train meta-learner models that can leverage prior semantic knowledge about novel classes to guide the classifier synthesis process. In particular, we propose semantically-conditioned feature attention and sample attention mechanisms that estimate the importance of representation dimensions and training instances. We also study the problem of sample noise in FSL, towards the utilization of meta-learners in more realistic and imperfect settings. Our experimental results demonstrate the effectiveness of the proposed semantic FSL model with and without sample noise.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 71 references that are in the map. First posted on arXiv 9 Jan 2022.
Builds on
37 of 71 references.
References · 37
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2017Non-local Neural Networkscited by 2,290
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2018On First-Order Meta-Learning Algorithmscited by 1,003
- 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
25 more
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
- 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
- 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
- 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
- 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
- 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
- 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
- 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
- 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
- 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
- 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
- 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
- 2020TaskNorm: Rethinking Batch Normalization for Meta-Learningcited by 50
- 2018Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networkscited by 35
- 2019Baby steps towards few-shot learning with multiple semanticscited by 29
- 2019Shaping Visual Representations with Language for Few-shot Classificationcited by 27
- 2018Open-Ended Content-Style Recombination Via Leakage Filteringcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.