On the generalization capabilities of FSL methods through domain adaptation: a case study in endoscopic kidney stone image classification

  title={On the generalization capabilities of FSL methods through domain adaptation: a case study in endoscopic kidney stone image classification},
  author={Mauricio Mendez-Ruiz and Francisco Javier Lopez-Tiro and Jonathan El Beze and Vincent Estrade and Gilberto Ochoa-Ruiz and Jacques Hubert and Andres Mendez-Vazquez and Christian Daul},
—Deep learning has shown great promise in diverse areas of computer vision, such as image classification, object detection and semantic segmentation, among many others. However, as it has been repeatedly demonstrated, deep learning methods trained on a dataset do not generalize well to datasets from other domains or even to similar datasets, due to data distribution shifts. In this work, we propose the use of a meta-learning based few-shot learning approach to alleviate these problems. In order… 

Figures and Tables from this paper



Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation

A deep stacked transformation approach for domain generalization that can be generalized to the design of highly robust deep segmentation models for clinical deployment and reaches the performance of state-of theart fully supervised models that are trained and tested on their source domains.

A New Benchmark for Evaluation of Cross-Domain Few-Shot Learning

The proposed CD-FSL benchmark is proposed, consisting of images from diverse domains with varying similarity to ImageNet, ranging from crop disease images, satellite images, and medical images, to serve as a challenging platform to guide future research on cross-domain few-shot learning due to its spectrum of diversity and coverage.

Assessing deep learning methods for the identification of kidney stones in endoscopic images

Five classification methods including deep convolutional neural networks (DCNN)-based approaches and traditional (non DCNN-based) ones are discussed and an XGBoost classifier exploiting well-chosen feature vectors can closely approach the performances of DCNN classifiers for a medical application with a limited number of annotated data is shown.

Towards an automated classification method for ureteroscopic kidney stone images using ensemble learning

Two effective supervised learning methods to automate and improve the accuracy of the classification of kidney stones; as well as a dataset consisting of kidney stone images captured with ureteroscopes are presented.

Self-Supervised Learning for Few-Shot Image Classification

This paper proposed to train a more generalized embedding network with self-supervised learning (SSL) which can provide robust representation for downstream tasks by learning from the data itself.

Metric learning for kidney stone classification

A new approach is proposed for a classifier, as a continuation of the mentioned attempt, using Metric learning techniques like Siamese and Triplet networks, which will result in an overall improvement from the current Machine learning techniques.

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

This work addresses the cross-domain few-shot learning (CDFSL) problem by boosting the generalization capability of the model by teaching the model to capture broader variations of the feature distributions with a novel noise-enhanced supervised autoencoder (NSAE).

A Closer Look at Few-shot Classification

The results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones, and a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.

Few-Shot Image Recognition by Predicting Parameters from Activations

A novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations is proposed, which achieves the state-of-the-art classification accuracy on Novel categories by a significant margin while keeping comparable performance on the large-scale categories.

myStone: A system for automatic kidney stone classification