Variational Few-Shot Learning
We propose a variational Bayesian framework for enhancing few-shot learning performance. This idea is motivated by the fact that single point based metric learning approaches are inherently noise-vulnerable and easy-to-be-biased. In a nutshell, stochastic variational inference is invoked to approximate bias-eliminated class specific sample distributions. In the meantime, a classifier-free prediction is attained by leveraging the distribution statistics on novel samples. Extensive experimental results on several benchmarks well demonstrate the effectiveness of our distribution-driven few-shot learning framework over previous point estimates based methods, in terms of superior classification accuracy and robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningMetric LearningVariational InferenceSimilar Papers 제목 키워드 기반
Task-Prior Conditional Variational Auto-Encoder for Few-Shot Image Classification
Transductive methods always outperform inductive methods in few-shot image classification scenarios. However, the existing few-shot methods contain a latent condition: the number of samples in each class is the same, whi…
Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage ClassificationLearning to Learn Variational Semantic Memory
In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The variational semantic memory accrues and stores semantic information for the probabilist…
Few-Shot LearningGeneral KnowledgeMeta-LearningVariational InferenceComposed Variational Natural Language Generation for Few-shot Intents
In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-shot intents, we consider an intent as a …
Intent DetectionText GenerationVCE: Variational Convertor-Encoder for One-Shot Generalization
Variational Convertor-Encoder (VCE) converts an image to various styles; we present this novel architecture for the problem of one-shot generalization and its transfer to new tasks not seen before without additional trai…
Few Shot Activity Recognition Using Variational Inference
There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of…
Action RecognitionActivity RecognitionFew-Shot LearningHuman Activity Recognition+1