DeepAI AI Chat
Log In Sign Up

Free Lunch for Few-shot Learning: Distribution Calibration

by   Shuo Yang, et al.
University of Technology Sydney

Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples, then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier. We assume every dimension in the feature representation follows a Gaussian distribution so that the mean and the variance of the distribution can borrow from that of similar classes whose statistics are better estimated with an adequate number of samples. Our method can be built on top of off-the-shelf pretrained feature extractors and classification models without extra parameters. We show that a simple logistic regression classifier trained using the features sampled from our calibrated distribution can outperform the state-of-the-art accuracy on two datasets ( 5 visualization of these generated features demonstrates that our calibrated distribution is an accurate estimation.


page 1

page 2

page 3

page 4


Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport

Few-shot classification aims to learn a classifier to recognize unseen c...

Bounds for the asymptotic distribution of the likelihood ratio

In this paper we give an explicit bound on the distance to chisquare for...

P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification

Nearest-Neighbor (NN) classification has been proven as a simple and eff...

Learnable Distribution Calibration for Few-Shot Class-Incremental Learning

Few-shot class-incremental learning (FSCIL) faces challenges of memorizi...

On discrimination between classes of distribution tails

We propose the test for distinguishing between two classes of distributi...

DCT-Net: Domain-Calibrated Translation for Portrait Stylization

This paper introduces DCT-Net, a novel image translation architecture fo...

Exploiting Unsupervised Inputs for Accurate Few-Shot Classification

In few-shot classification, the aim is to learn models able to discrimin...