SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification

by   Mauricio Mendez-Ruiza, et al.

Few-shot learning is a challenging area of research that aims to learn new concepts with only a few labeled samples of data. Recent works based on metric-learning approaches leverage the meta-learning approach, which is encompassed by episodic tasks that make use a support (training) and query set (test) with the objective of learning a similarity comparison metric between those sets. Due to the lack of data, the learning process of the embedding network becomes an important part of the few-shot task. Previous works have addressed this problem using metric learning approaches, but the properties of the underlying latent space and the separability of the difference classes on it was not entirely enforced. In this work, we propose two different loss functions which consider the importance of the embedding vectors by looking at the intra-class and inter-class distance between the few data. The first loss function is the Proto-Triplet Loss, which is based on the original triplet loss with the modifications needed to better work on few-shot scenarios. The second loss function, which we dub ICNN loss is based on an inter and intra class nearest neighbors score, which help us to assess the quality of embeddings obtained from the trained network. Our results, obtained from a extensive experimental setup show a significant improvement in accuracy in the miniImagenNet benchmark compared to other metric-based few-shot learning methods by a margin of 2 to allow the network to generalize better to previously unseen classes. In our experiments, we demonstrate competitive generalization capabilities to other domains, such as the Caltech CUB, Dogs and Cars datasets compared with the state of the art.


page 11

page 12


Revisiting Metric Learning for Few-Shot Image Classification

The goal of few-shot learning is to recognize new visual concepts with j...

Constellation Loss: Improving the efficiency of deep metric learning loss functions for optimal embedding

Metric learning has become an attractive field for research on the lates...

Hyperspherical embedding for novel class classification

Deep learning models have become increasingly useful in many different i...

SetMargin Loss applied to Deep Keystroke Biometrics with Circle Packing Interpretation

This work presents a new deep learning approach for keystroke biometrics...

Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining

Few-shot learning aims to generalize unseen classes that appear during t...

Multi-level Distance Regularization for Deep Metric Learning

We propose a novel distance-based regularization method for deep metric ...

HSADML: Hyper-Sphere Angular Deep Metric based Learning for Brain Tumor Classification

Brain Tumors are abnormal mass of clustered cells penetrating regions of...

Please sign up or login with your details

Forgot password? Click here to reset