Few-Shot Learning with Metric-Agnostic Conditional Embeddings

02/12/2018
by   Nathan Hilliard, et al.
0

Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison. This allows the network to decide what aspects of each class are important for the comparison at hand. We find that this flexible architecture works well in practice, achieving state-of-the-art performance on the Caltech-UCSD birds fine-grained classification task.

READ FULL TEXT
research
01/26/2019

Few-shot Learning with Meta Metric Learners

Few-shot Learning aims to learn classifiers for new classes with only a ...
research
05/10/2019

Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training

We propose a method for learning embeddings for few-shot learning that i...
research
06/08/2022

Metric Based Few-Shot Graph Classification

Many modern deep-learning techniques do not work without enormous datase...
research
11/11/2017

Towards ECDSA key derivation from deep embeddings for novel Blockchain applications

In this work, we propose a straightforward method to derive Elliptic Cur...
research
05/04/2020

One-Shot Image Classification by Learning to Restore Prototypes

One-shot image classification aims to train image classifiers over the d...
research
12/07/2019

Improved Few-Shot Visual Classification

Few-shot learning is a fundamental task in computer vision that carries ...
research
07/11/2020

ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification

Face verification can be regarded as a 2-class fine-grained visual recog...

Please sign up or login with your details

Forgot password? Click here to reset