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.
16
mentions
1
contributor
Cite this software
Choose a version:
- [[release.tag]]
DOI:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Choose a reference manager file format:
- [[ format.displayName ]]
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
Programming Language
- Python
License
- MIT
Source code
Participating organizations
Mentions
-
D2.1 Progress Report (Use Cases #1-5)October 31, 2018
-
D2.2 Progress report (UC#1-5) - updateOctober 31, 2019
-
D3.1 Performance Modelling and PredictionJanuary 31, 2019
-
D4.1 Initial state of the art and requirements analysis, initial PROCESS architectureApril 30, 2018
-
D4.3 Updated Requirements Analysis, Validation of 1st Prototype and Updated PROCESS ArchitectureApril 30, 2019
-
D4.5 Validation of 2nd prototype and final PROCESS architectureJanuary 31, 2020
-
D8.1 Validation Report of 1st PROCESS UpdateJuly 31, 2019
Projects with Regression Concept Vectors (RCVs)
Contributors
-
Mara GrazianiHaute École Spécialisée de Suisse Occidentale HES-SO Valais (HESSO)
Contact person
Information for page maintainers
OAI-PMH metadata:
OK
citation metadata:
no valid CITATION.cff found in any release.