Adaptive Poincaré Point to Set Distance for Few-Shot Classification

12/03/2021
by   Rongkai Ma, et al.
0

Learning and generalizing from limited examples, i,e, few-shot learning, is of core importance to many real-world vision applications. A principal way of achieving few-shot learning is to realize an embedding where samples from different classes are distinctive. Recent studies suggest that embedding via hyperbolic geometry enjoys low distortion for hierarchical and structured data, making it suitable for few-shot learning. In this paper, we propose to learn a context-aware hyperbolic metric to characterize the distance between a point and a set associated with a learned set to set distance. To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively and based on the constellation of the points. This not only makes the metric local but also dependent on the task in hand, meaning that the metric will adapt depending on the samples that it compares. We empirically show that such metric yields robustness in the presence of outliers and achieves a tangible improvement over baseline models. This includes the state-of-the-art results on five popular few-shot classification benchmarks, namely mini-ImageNet, tiered-ImageNet, Caltech-UCSD Birds-200-2011 (CUB), CIFAR-FS, and FC100.

READ FULL TEXT
research
12/07/2021

Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning

Learning and generalizing to novel concepts with few samples (Few-Shot L...
research
05/23/2018

TADAM: Task dependent adaptive metric for improved few-shot learning

Few-shot learning has become essential for producing models that general...
research
08/09/2021

Transductive Few-Shot Classification on the Oblique Manifold

Few-shot learning (FSL) attempts to learn with limited data. In this wor...
research
08/09/2017

Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

We propose a novel architecture for k-shot classification on the Omniglo...
research
11/02/2022

Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective

Few-shot learning problem focuses on recognizing unseen classes given a ...
research
10/27/2016

Local Similarity-Aware Deep Feature Embedding

Existing deep embedding methods in vision tasks are capable of learning ...
research
02/18/2023

An Adaptive Plug-and-Play Network for Few-Shot Learning

Few-shot learning (FSL) requires a model to classify new samples after l...

Please sign up or login with your details

Forgot password? Click here to reset