Improving the explain-any-concept by introducing nonlinearity to the trainable surrogate model

Name: Improving the explain-any-concept by introducing nonlinearity to the trainable surrogate model
Author: Ozer, Sedat, Zaval, Mounes

İsim	Improving the explain-any-concept by introducing nonlinearity to the trainable surrogate model
Yazar	Ozer, Sedat, Zaval, Mounes
Basım Tarihi:	2024-01-01
Basım Yeri	- IEEE
Konu	SAM, Explain-Any-Concept, XAI, Explainability
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-835038896-1
Kayıt Numarası	5ae8b083-3567-49b7-b77b-e6fa4ab030b8
Lokasyon	Computer Science
Tarih	2024-01-01
Örnek Metin	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

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Improving the explain-any-concept by introducing nonlinearity to the trainable surrogate model

Yazar Ozer, Sedat, Zaval, Mounes

Basım Tarihi 2024-01-01

Basım Yeri - IEEE

Konu SAM, Explain-Any-Concept, XAI, Explainability

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-835038896-1

Kayıt Numarası 5ae8b083-3567-49b7-b77b-e6fa4ab030b8

Lokasyon Computer Science

Tarih 2024-01-01

Örnek Metin 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