Few-Shot Learning with Meta Metric Learners
نویسندگان
چکیده
Existing few-shot learning approaches are based on either meta-learning or metriclearning, which would suffer if the tasks have varying numbers of classes and/or the tasks diverge significantly. We propose meta metric learning to deal with the limitations of the existing few-shot learning approaches. Our meta metric learning approach consists of two components, task-specific learners that exploit metric learning to handle flexible numbers of classes across tasks, and a meta-learner that learns and specifies the metrics in the task-specific learners. We test our approach in the new realistic few-shot setting with more diverse tasks and flexible class numbers and obtains superior performance.
منابع مشابه
Meta-SGD: Learning to Learn Quickly for Few Shot Learning
Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial. In this paper, we develop Meta-SGD, an SGD-like, easily trainable meta-learner that can initial...
متن کاملFew-shot Learning
Though deep neural networks have shown great success in the large data domain, they generally perform poorly on few-shot learning tasks, where a classifier has to quickly generalize after seeing very few examples from each class. The general belief is that gradient-based optimization in high capacity classifiers requires many iterative steps over many examples to perform well. Here, we propose ...
متن کاملLow-Shot Learning from Imaginary Data
Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses thi...
متن کاملContinuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence. In this paper, we cast the problem of continuous adaptation into the learning-to-learn framework. We develop a simple gradient-based meta-learning algorithm suitable for adaptation in dynamically changing and adversarial scenarios. Add...
متن کاملLearning to Compare: Relation Network for Few-Shot Learning
We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is de...
متن کامل