Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning

by   Henry Kvinge, et al.

Deep learning has shown great success in settings with massive amounts of data but has struggled when data is limited. Few-shot learning algorithms, which seek to address this limitation, are designed to generalize well to new tasks with limited data. Typically, models are evaluated on unseen classes and datasets that are defined by the same fundamental task as they are trained for (e.g. category membership). One can also ask how well a model can generalize to fundamentally different tasks within a fixed dataset (for example: moving from category membership to tasks that involve detecting object orientation or quantity). To formalize this kind of shift we define a notion of "independence of tasks" and identify three new sets of labels for established computer vision datasets that test a model's ability to generalize to tasks which draw on orthogonal attributes in the data. We use these datasets to investigate the failure modes of metric-based few-shot models. Based on our findings, we introduce a new few-shot model called Fuzzy Simplicial Networks (FSN) which leverages a construction from topology to more flexibly represent each class from limited data. In particular, FSN models can not only form multiple representations for a given class but can also begin to capture the low-dimensional structure which characterizes class manifolds in the encoded space of deep networks. We show that FSN outperforms state-of-the-art models on the challenging tasks we introduce in this paper while remaining competitive on standard few-shot benchmarks.


Flexible Few-Shot Learning with Contextual Similarity

Existing approaches to few-shot learning deal with tasks that have persi...

Metalearning with Hebbian Fast Weights

We unify recent neural approaches to one-shot learning with older ideas ...

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Few-shot learning is an important area of research. Conceptually, humans...

Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach

The field of visual few-shot classification aims at transferring the sta...

Interval Bound Propagationx2013aided Fewx002dshot Learning

Few-shot learning aims to transfer the knowledge acquired from training ...

Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning

Few-shot learning aims to classify unseen classes with a few training ex...

Task Discovery: Finding the Tasks that Neural Networks Generalize on

When developing deep learning models, we usually decide what task we wan...

Please sign up or login with your details

Forgot password? Click here to reset