Network dissection: Quantifying interpretability of deep visual representations
CVPR'17, 2017. [All Versions]. [Project]. [Dataset: Places365]. The original paper on visualizing the class activation maps to explain convolutional neural networks.
- from
- AGI & CoCoSci
- added
- 2026-10-10
- likes
- 0
similar
-
[Paper ICONIP-2014] brml.org
-
Visual Commonsense R-CNN ieeexplore.ieee.org
CVPR'20, 2020. [All Versions].
-
Visual Complexity. An Exploration on Mapping Complex Networks visualcomplexity.com
-
This Looks Like That: Deep Learning for Interpretable Image Recognition papers.neurips.cc
NeurIPS'19, 2019. [All Versions].
-
[Paper-arXiv15] arxiv.org
-
[Paper-ICML12] yann.lecun.com
AGI & CoCoSci › Papers > Explainability > Explainable Deep Learning: “CVPR'17, 2017. [All Versions]. [Project]. [Dataset: Places365]. The original paper on visualizing the class activation maps to explain convolutional neural networks.”