Task Adaptive Feature Transformation for One-Shot Learning

We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes. Our norm-induced transformation could be understood as a re-parametrization of...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-04
Main Authors: Imtiaz Masud Ziko, Lecue, Freddy, Ismail Ben Ayed
Format: Article
Language:English
Subjects:
Cluster analysis
Clustering
Entropy
Inference
Optimization
Parameterization
Transformations
Vector quantization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes. Our norm-induced transformation could be understood as a re-parametrization of the feature space to disentangle the representations of different classes in a task specific manner. It focuses on the relevant feature dimensions while hindering the effects of non-relevant dimensions that may cause overfitting in a one-shot setting. We also provide an interpretation of our proposed feature transformation in the basic case of few-shot inference with K-means clustering. Furthermore, we give an interesting bound-optimization link between K-means and entropy minimization. This emphasizes why our feature transformation is useful in the context of entropy minimization. We report comprehensive experiments, which show consistent improvements over a variety of one-shot benchmarks, outperforming recent state-of-the-art methods.
ISSN:2331-8422