Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning

03/28/2019
by   Wenbin Li, et al.
0

Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class. Recent work has achieved promising classification performance, where an image-level feature based measure is usually used. In this paper, we argue that a measure at such a level may not be effective enough in light of the scarcity of examples in few-shot learning. Instead, we think a local descriptor based image-to-class measure should be taken, inspired by its surprising success in the heydays of local invariant features. Specifically, building upon the recent episodic training mechanism, we propose a Deep Nearest Neighbor Neural Network (DN4 in short) and train it in an end-to-end manner. Its key difference from the literature is the replacement of the image-level feature based measure in the final layer by a local descriptor based image-to-class measure. This measure is conducted online via a k-nearest neighbor search over the deep local descriptors of convolutional feature maps. The proposed DN4 not only learns the optimal deep local descriptors for the image-to-class measure, but also utilizes the higher efficiency of such a measure in the case of example scarcity, thanks to the exchangeability of visual patterns across the images in the same class. Our work leads to a simple, effective, and computationally efficient framework for few-shot learning. Experimental study on benchmark datasets consistently shows its superiority over the related state-of-the-art, with the largest absolute improvement of 17% over the next best. The source code can be available from https://github.com/WenbinLee/DN4.git.

READ FULL TEXT
research
11/12/2019

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

Few-shot learners aim to recognize new object classes based on a small n...
research
05/22/2018

AffinityNet: semi-supervised few-shot learning for disease type prediction

Motivation:While deep learning has achieved great success in computer vi...
research
03/30/2021

Revisiting Deep Local Descriptor for Improved Few-Shot Classification

Few-shot classification studies the problem of quickly adapting a deep l...
research
11/28/2022

RankDNN: Learning to Rank for Few-shot Learning

This paper introduces a new few-shot learning pipeline that casts releva...
research
05/15/2023

Learning More Discriminative Local Descriptors for Few-shot Learning

Few-shot learning for image classification comes up as a hot topic in co...
research
12/19/2017

Learning with Imprinted Weights

Human vision is able to immediately recognize novel visual categories af...
research
12/01/2011

Local Naive Bayes Nearest Neighbor for Image Classification

We present Local Naive Bayes Nearest Neighbor, an improvement to the NBN...

Please sign up or login with your details

Forgot password? Click here to reset