|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.
#2 best model for Few-Shot Image Classification on OMNIGLOT - 5-Shot, 5-way
By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
SOTA for Language Modelling on Penn Treebank (Word Level) (using extra training data)
COMMON SENSE REASONING COREFERENCE RESOLUTION DOMAIN ADAPTATION FEW-SHOT LEARNING LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SENTENCE COMPLETION UNSUPERVISED MACHINE TRANSLATION WORD SENSE DISAMBIGUATION
We conclude with a discussion of the rapid learning vs feature reuse question for meta-learning algorithms more broadly.
This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i. e., learns quickly) when presented with a previously unseen task sampled from this distribution.
#3 best model for Image Classification on Tiered ImageNet 5-way (5-shot)
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.
#2 best model for Few-Shot Image Classification on Mini-Imagenet 20-way (1-shot)
We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.
Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.
#2 best model for Image Classification on Tiered ImageNet 5-way (5-shot)
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
#2 best model for Few-Shot Image Classification on Mini-ImageNet-CUB 5-way (5-shot)
We conduct detailed analysis of the main components that lead to high transfer performance.
SOTA for Image Classification on ObjectNet (Bounding Box) (using extra training data)