Author
Ozer, Sedat, Zaval, Mounes
Publication Date
2024-01-01
Publication Place
-
IEEE
Subject
SAM, Explain-Any-Concept, XAI, Explainability
Type
Document
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
979-835038896-1
Record ID
5ae8b083-3567-49b7-b77b-e6fa4ab030b8
Library Location
Computer Science
Date
2024-01-01
Sample Text
In the evolving field of Explainable AI (XAI), interpreting the decisions of deep neural networks (DNNs) in computer vision tasks is an important process. While pixel-based XAI methods focus on identifying significant pixels, existing concept-based XAI methods use pre-defined or human-annotated concepts. The recently proposed Segment Anything Model (SAM) achieved a significant step forward to prepare automatic concept sets via comprehensive instance segmentation. Building upon this, the Explain Any Concept (EAC) model emerged as a flexible method for explaining DNN decisions. EAC model is based on using a surrogate model which has one trainable linear layer to simulate the target model. In this paper, by introducing an additional nonlinear layer to the original surrogate model, we show that we can improve the performance of the EAC model. We compare our proposed approach to the original EAC model and report improvements obtained on both ImageNet and MS COCO datasets.
DOI
10.1109/SIU61531.2024.10600959
