Few-Shot Learning Through an Information Retrieval Lens
arXiv:1707.02610
Abstract
Few-shot learning refers to understanding new concepts from only a few examples. We propose an information retrieval-inspired approach for this problem that is motivated by the increased importance of maximally leveraging all the available information in this low-data regime. We define a training objective that aims to extract as much information as possible from each training batch by effectively optimizing over all relative orderings of the batch points simultaneously. In particular, we view each batch point as a `query' that ranks the remaining ones based on its predicted relevance to them and we define a model within the framework of structured prediction to optimize mean Average Precision over these rankings. Our method achieves impressive results on the standard few-shot classification benchmarks while is also capable of few-shot retrieval.
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Matching Networks for One Shot Learning
- A Survey on Metric Learning for Feature Vectors and Structured Data
- Learning to Remember Rare Events
- Attentive Recurrent Comparators
- Training Deep Neural Networks via Direct Loss Minimization
Cited by in corpus (15)
- SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
- Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
- One-Shot Instance Segmentation
- LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
- The Variational Homoencoder: Learning to learn high capacity generative models from few examples
- Unsupervised State Representation Learning in Atari
- Diverse Few-Shot Text Classification with Multiple Metrics
- Reconciling meta-learning and continual learning with online mixtures of tasks
- Deep Learning in Information Security
- NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature
- Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
- One-Shot Segmentation in Clutter
- SynSig2Vec: Learning Representations from Synthetic Dynamic Signatures for Real-world Verification
- Towards Robust Pattern Recognition: A Review
- DAMSL: Domain Agnostic Meta Score-based Learning