NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification

06/13/2021
by   Weichuan Zhang, et al.
0

Metric-based few-shot fine-grained image classification (FSFGIC) aims to learn a transferable feature embedding network by estimating the similarities between query images and support classes from very few examples. In this work, we propose, for the first time, to introduce the non-linear data projection concept into the design of FSFGIC architecture in order to address the limited sample problem in few-shot learning and at the same time to increase the discriminability of the model for fine-grained image classification. Specifically, we first design a feature re-abstraction embedding network that has the ability to not only obtain the required semantic features for effective metric learning but also re-enhance such features with finer details from input images. Then the descriptors of the query images and the support classes are projected into different non-linear spaces in our proposed similarity metric learning network to learn discriminative projection factors. This design can effectively operate in the challenging and restricted condition of a FSFGIC task for making the distance between the samples within the same class smaller and the distance between samples from different classes larger and for reducing the coupling relationship between samples from different categories. Furthermore, a novel similarity measure based on the proposed non-linear data project is presented for evaluating the relationships of feature information between a query image and a support set. It is worth to note that our proposed architecture can be easily embedded into any episodic training mechanisms for end-to-end training from scratch. Extensive experiments on FSFGIC tasks demonstrate the superiority of the proposed methods over the state-of-the-art benchmarks.

READ FULL TEXT

page 3

page 5

research
07/06/2019

Revisiting Metric Learning for Few-Shot Image Classification

The goal of few-shot learning is to recognize new visual concepts with j...
research
10/09/2020

Uncertainty-Aware Few-Shot Image Classification

Few-shot image classification aims to learn to recognize new categories ...
research
08/04/2017

Hierarchical Metric Learning for Fine Grained Image Classification

This paper deals with the problem of fine-grained image classification a...
research
12/11/2019

Associative Alignment for Few-shot Image Classification

Few-shot image classification aims at training a model by using only a f...
research
09/21/2022

Query-Guided Networks for Few-shot Fine-grained Classification and Person Search

Few-shot fine-grained classification and person search appear as distinc...
research
09/08/2020

Region Comparison Network for Interpretable Few-shot Image Classification

While deep learning has been successfully applied to many real-world com...
research
04/09/2022

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

Few-shot classification is a challenging problem as only very few traini...

Please sign up or login with your details

Forgot password? Click here to reset