Improving Classification Accuracy With Graph Filtering - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Improving Classification Accuracy With Graph Filtering

Résumé

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 variance, while maintaining the mean. While our approach applies to all classification problems in general, it is particularly useful in few-shot settings, where intra-class noise can have a huge impact due to the small sample selection. Using standardized benchmarks in the field of vision, we empirically demonstrate the ability of the proposed method to slightly improve state-of-the-art results in both cases of few-shot and standard classification.

Dates et versions

hal-03675142 , version 1 (22-05-2022)

Identifiants

Citer

M. Hamidouche, C. Lassance, Y. Hu, Lucas Drumetz, Bastien Pasdeloup, et al.. Improving Classification Accuracy With Graph Filtering. ICIP 2021: IEEE International Conference on Image Processing, Sep 2021, Anchorage, United States. pp.334-338, ⟨10.1109/ICIP42928.2021.9506042⟩. ⟨hal-03675142⟩
24 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More