Search Results for author:
Found 8 papers, 4 papers with code
On the stability, correctness and plausibility of visual explanation methods based on feature importance
In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w. r. t.
H²O: Heatmap by Hierarchical Occlusion
We also propose two new pairs of metrics that overcome some evaluation issues: (a) Insertion and Deletion Spearman correlation coefficients which both estimate a correlation between the computed scores in a saliency map and the importance for the model of the associated pixels in the image.
State of the Art of Visual Analytics for eXplainable Deep Learning
The survey concludes by identifying future research challenges and bridging activities that are helpful to strengthen the role of Visual Analytics as effective support for eXplainable Deep Learning and to foster the adoption of Visual Analytics solutions in the eXplainable Deep Learning community.
FORBID: Fast Overlap Removal By stochastic gradIent Descent for Graph Drawing
While many graph drawing algorithms consider nodes as points, graph visualization tools often represent them as shapes.
Deep Neural Network for DrawiNg Networks, (DNN)^2
We demonstrate that it is possible to use DL techniques to learn a graph-to-layout sequence of operations thanks to a graph-related objective function.
Impacts of the Numbers of Colors and Shapes on Outlier Detection: from Automated to User Evaluation
When encoded with one attribute, the difficulty depends on that attribute heterogeneity until its capacity limit (7 for color, 5 for shape) is reached.
Features Understanding in 3D CNNs for Actions Recognition in Video
Features visualization is performed at the RGB and Optical flow branches of the network.
CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge
This paper presents our contribution to the DeepGlobe Building Detection Challenge.
