A Feature Generator for Few-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Few-shot learning (FSL) aims to enable models to recognize novel objects or classes with limited labelled data. Feature generators, which synthesize new data points to augment limited datasets, have emerged as a promising solution to this challenge. This paper investigates the effectiveness of feature generators in enhancing the embedding process for FSL tasks. To address the issue of inaccurate embeddings due to the scarcity of images per class, we introduce a feature generator that creates visual features from class-level textual descriptions. By training the generator with a combination of classifier loss, discriminator loss, and distance loss between the generated features and true class embeddings, we ensure the generation of accurate same-class features and enhance the overall feature representation. Our results show a significant improvement in accuracy over baseline methods, with our approach outperforming the baseline model by 10% in 1-shot and around 5% in 5-shot approaches. Additionally, both visual-only and visual + textual generators have also been tested in this paper. The code is publicly available at https://github.com/heethanjan/Feature-Generator-for-FSL.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 21 Sep 2024.
Builds on
31 of 41 references.
References · 31
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 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
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 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
- 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
- 2017Data Augmentation Generative Adversarial Networkscited by 278
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
19 more
- 2019Cross Attention Network for Few-shot Classificationcited by 218
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
- 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
- 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
- 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
- 2019Shadow Removal via Shadow Image Decompositioncited by 96
- 2019Prototype Rectification for Few-Shot Learningcited by 96
- 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
- 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
- 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
- 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
- 2022Generating Representative Samples for Few-Shot Classificationcited by 39
- 2020Physics-based Shadow Image Decomposition for Shadow Removalcited by 38
- 2021Meta-learning with implicit gradients in a few-shot setting for medical image segmentationcited by 15
- 2016Co-localization with Category-Consistent Features and Geodesic Distance Propagationcited by 14
- 2021Label Hallucination for Few-Shot Classificationcited by 11
- 2017Geodesic Distance Histogram Feature for Video Segmentationcited by 6
Built on by
Not cited yet.