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

By Avinash Ravichandran, Rahul Bhotika, Stefano Soatto. 2019

192 citations recorded by the source corpus.

We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) and learn the prototypes along with the model parameters. The class representation function is defined implicitly, which allows us to deal with a variable number of shots per class with a simple constant-size architecture. The class embedding encompasses metric learning, that facilitates adding new classes without crowding the class representation space. Despite being general and not tuned to the benchmark, our approach achieves state-of-the-art performance on the standard few-shot benchmark datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020, methodology): “30 Shot-Free [41] ResNet-12 59.”
Incremental Few-Shot Object Detection (2020, neutral): “Note that there are many more recent FSL methods [6, 26, 7, 17, 47, 55, 50, 27, 39, 11, 16] that produce better performance on image classification tasks than MAML.”
Incremental Meta-Learning via Indirect Discriminant Alignment (2020, methodology): “Each function can be fixed [35] or learned [25].”
A Baseline for Few-Shot Image Classification (2019, background): “A number of recent results build upon this idea with increasing levels of sophistication in how they learn the embedding [14, 16, 17], creating exemplars from the support set and picking a metric for the embedding [18, 17, 19].”
Few-Shot Learning With a Strong Teacher (2021, background): “The inﬂuence of the number of shots (e.g., between meta-training and meta-testing) is discussed in [28], [83], [84].”
On Episodes, Prototypical Networks, and Few-shot Learning (2020, unknown): “tieredImageNet Method 1-shot 5-shot Shot-Free (Ravichandran et al., 2019) 63.”
Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness (2021, unknown): “Representative works include [56, 51, 19, 20, 22, 48, 7, 41, 6, 40, 36, 60, 45, 52, 64], etc.”
Boosting Few-Shot Learning With Adaptive Margin Loss (2020, unknown): “10 ECMSFMT [24] ResNet12 Metric 59.”
Few-Shot Open-Set Recognition Using Meta-Learning (2020, background): “Few-Shot Learning: Extensive research on few-shot learning [26, 4, 34, 30, 32, 27, 7, 23, 16, 2] has emerged in recent years.”
Transforming task representations to perform novel tasks (2020, background): “First, there is a large body of prior work on allowing models to learn to behave more ﬂexibly, for example by metalearning, that is, learning to learn from examples (9, 27, 29).”