arXiv Open Access 2021

TorchPRISM: Principal Image Sections Mapping, a novel method for Convolutional Neural Network features visualization

Tomasz Szandala
Lihat Sumber

Abstrak

In this paper we introduce a tool called Principal Image Sections Mapping - PRISM, dedicated for PyTorch, but can be easily ported to other deep learning frameworks. Presented software relies on Principal Component Analysis to visualize the most significant features recognized by a given Convolutional Neural Network. Moreover, it allows to display comparative set features between images processed in the same batch, therefore PRISM can be a method well synerging with technique Explanation by Example.

Topik & Kata Kunci

Penulis (1)

T

Tomasz Szandala

Format Sitasi

Szandala, T. (2021). TorchPRISM: Principal Image Sections Mapping, a novel method for Convolutional Neural Network features visualization. https://arxiv.org/abs/2101.11266

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓