A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2016
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914775190994944 |
|---|---|
| author | Grün, Felix Rupprecht, Christian Navab, Nassir Tombari, Federico |
| author_facet | Grün, Felix Rupprecht, Christian Navab, Nassir Tombari, Federico |
| contents | Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of groups have recently proposed different methods to visualize the learned models. In this work we suggest a general taxonomy to classify and compare these methods, subdividing the literature into three main categories and providing researchers with a terminology to base their works on. Furthermore, we introduce the FeatureVis library for MatConvNet: an extendable, easy to use open source library for visualizing CNNs. It contains implementations from each of the three main classes of visualization methods and serves as a useful tool for an enhanced understanding of the features learned by intermediate layers, as well as for the analysis of why a network might fail for certain examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1606_07757 |
| institution | arXiv |
| publishDate | 2016 |
| record_format | arxiv |
| spellingShingle | A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks Grün, Felix Rupprecht, Christian Navab, Nassir Tombari, Federico Computer Vision and Pattern Recognition Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of groups have recently proposed different methods to visualize the learned models. In this work we suggest a general taxonomy to classify and compare these methods, subdividing the literature into three main categories and providing researchers with a terminology to base their works on. Furthermore, we introduce the FeatureVis library for MatConvNet: an extendable, easy to use open source library for visualizing CNNs. It contains implementations from each of the three main classes of visualization methods and serves as a useful tool for an enhanced understanding of the features learned by intermediate layers, as well as for the analysis of why a network might fail for certain examples. |
| title | A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/1606.07757 |