PROCESS
Providing computing solutions for exascale challenges
Regression Concept Vectors (RCVs)
This repository contains the development of the interpretability and perturbation robustness for the analysis of histopathology images by convolutional neural networks.
2
mentions
1
contributor
What Regression Concept Vectors (RCVs) can do for you
- Extraction of concept measures from manual nuclei annotations
- Correlation analysis between concepts and network prediction
- Analysis of the concept learning dynamics during training
- Perturbation analysis by bidirectional relevance scores
Recent work on Testing with Concept Activation Vectors (TCAV) proposed directional derivatives to quantify the in uence of user-defined concepts on the network output [1]. However, diagnostic concepts are often continuous measures that might be counter intuitive to describe by their presence or absence. In this paper, we extend TCAV from a classification problem to a regression problem by computing Regression Concept Vectors (RCVs). Instead of seeking a discriminator between two concepts, we seek the direction of greatest increase of the measures for a single continuous concept. We measure the relevance of a concept with bidirectional relevance scores, Br. The Br scores assume positive values when increasing values of the concept measures positively affect classification and negative in the opposite case.
Tags
No tags availableProgramming Language
- Python
License
- MIT
Source code
Participating organizations
Projects with Regression Concept Vectors (RCVs)
Contributors
-
Mara GrazianiHaute École Spécialisée de Suisse Occidentale HES-SO Valais (HESSO)
Contact person
