Few-shot Classification via Ensemble Learning with Multi-Order Statistics
Not on the map. Why?
Abstract (arXiv)
Transfer learning has been widely adopted for few-shot classification. Recent studies reveal that obtaining good generalization representation of images on novel classes is the key to improving the few-shot classification accuracy. To address this need, we prove theoretically that leveraging ensemble learning on the base classes can correspondingly reduce the true error in the novel classes. Following this principle, a novel method named Ensemble Learning with Multi-Order Statistics (ELMOS) is proposed in this paper. In this method, after the backbone network, we use multiple branches to create the individual learners in the ensemble learning, with the goal to reduce the storage cost. We then introduce different order statistics pooling in each branch to increase the diversity of the individual learners. The learners are optimized with supervised losses during the pre-training phase. After pre-training, features from different branches are concatenated for classifier evaluation. Extensive experiments demonstrate that each branch can complement the others and our method can produce a state-of-the-art performance on multiple few-shot classification benchmark datasets.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 30 Apr 2023.
Builds on
33 of 55 references.
References · 33
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2019A Closer Look at Few-shot Classificationcited by 684
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
- 2018Meta-learning with differentiable closed-form solverscited by 397
- 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
- 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
- 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
- 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
- 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
21 more
- 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
- 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
- 2021Relational Embedding for Few-Shot Classificationcited by 74
- 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
- 2019Associative Alignment for Few-shot Image Classificationcited by 58
- 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
- 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
- 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
- 2021Boosting Randomized Smoothing with Variance Reduced Classifierscited by 47
- 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
- 2020Self-supervised Knowledge Distillation for Few-shot Learningcited by 41
- 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
- 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
- 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
- 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
- 2020Cooperative Bi-path Metric for Few-shot Learningcited by 15
- 2021Adaptive Poincar'e Point to Set Distance for Few-Shot Classificationcited by 15
- 2021Hybrid Graph Neural Networks for Few-Shot Learningcited by 15
- 2020Improving Few-Shot Learning through Multi-task Representation Learning Theorycited by 7
- 2021Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learningcited by 4
- 2021Exploring Category-correlated Feature for Few-shot Image Classificationcited by 4
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.