Improving Classification Accuracy With Graph Filtering

  title={Improving Classification Accuracy With Graph Filtering},
  author={Mounia Hamidouche and C. Lassance and Yuqing Hu and Lucas Drumetz and Bastien Pasdeloup and Vincent Gripon},
  journal={2021 IEEE International Conference on Image Processing (ICIP)},
In machine learning, classifiers are typically susceptible to noise in the training data. In this work, we aim at reducing intra-class noise with the help of graph filtering to improve the classification performance. Considered graphs are obtained by connecting samples of the training set that belong to a same class depending on the similarity of their representation in a latent space. We show that the proposed graph filtering methodology has the effect of asymptotically reducing intra-class… 

Figures and Tables from this paper


The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
This tutorial overview outlines the main challenges of the emerging field of signal processing on graphs, discusses different ways to define graph spectral domains, which are the analogs to the classical frequency domain, and highlights the importance of incorporating the irregular structures of graph data domains when processing signals on graphs.
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
A transfer-based novel method that builds on two steps: preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and leveraging this preprocessing using an optimal-transport inspired algorithm.
Wide Residual Networks
This paper conducts a detailed experimental study on the architecture of ResNet blocks and proposes a novel architecture where the depth and width of residual networks are decreased and the resulting network structures are called wide residual networks (WRNs), which are far superior over their commonly used thin and very deep counterparts.
Fast AutoAugment
This paper proposes an algorithm called Fast AutoAugment that finds effective augmentation policies via a more efficient search strategy based on density matching that speeds up the search time by orders of magnitude while achieves comparable performances on image recognition tasks with various models and datasets.
Object Detection With Deep Learning: A Review
This paper provides a review of deep learning-based object detection frameworks and focuses on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further.
Meta-learning with differentiable closed-form solvers
The main idea is to teach a deep network to use standard machine learning tools, such as ridge regression, as part of its own internal model, enabling it to quickly adapt to novel data.
Graph Signal Processing: Overview, Challenges, and Applications
An overview of core ideas in GSP and their connection to conventional digital signal processing are provided, along with a brief historical perspective to highlight how concepts recently developed build on top of prior research in other areas.
Meta-Learning for Semi-Supervised Few-Shot Classification
This work proposes novel extensions of Prototypical Networks that are augmented with the ability to use unlabeled examples when producing prototypes, and confirms that these models can learn to improve their predictions due to unlabeling examples, much like a semi-supervised algorithm would.
Shake-Shake regularization
The method introduced in this paper aims at helping deep learning practitioners faced with an overfit problem. The idea is to replace, in a multi-branch network, the standard summation of parallel
Deep Pyramidal Residual Networks
This research gradually increases the feature map dimension at all units to involve as many locations as possible in the network architecture and proposes a novel residual unit capable of further improving the classification accuracy with the new network architecture.