paper-with-me

홈 › Papers

Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces

2023-04-30 · Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade

Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what CNNs have learned are primarily based on performance metrics, because these allow, e.g., for cross-architecture CNN comparison. However, these neglect how knowledge is stored inside. To tackle this yet unsolved problem, our work proposes two methods for estimating the layer-wise similarity between semantic information inside CNN latent spaces. These allow insights into both the flow and likeness of semantic information within CNN layers, and into the degree of their similarity between different network architectures. As a basis, we use two renowned explainable artificial intelligence (XAI) techniques, which are used to obtain concept activation vectors, i.e., global vector representations in the latent space. These are compared with respect to their activation on test inputs. When applied to three diverse object detectors and two datasets, our methods reveal that (1) similar semantic concepts are learned regardless of the CNN architecture, and (2) similar concepts emerge in similar relative layer depth, independent of the total number of layers. Finally, our approach poses a promising step towards semantic model comparability and comprehension of how different CNNs process semantic information.

📄 PDF Abstract BibTeX arXiv:2305.07663

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Model Selection

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Interpretable Convolutional Neural Networks

2017-10-02 · CVPR 2018 6 · Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each fi…

Objectsingle catogory classification

An Interpretable Neuron Embedding for Static Knowledge Distillation

2022-11-14 · Wei Han, Yangqiming Wang, Christian Böhm, Junming Shao

Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretable neural network method, by embedding n…

Knowledge Distillation

Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning

2021-06-05 · Yilin Wang, Shaozuo Yu, Xiaokang Yang, Wei Shen

In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy. We achieve this by building a differentiable deci…

Classification

Network Inversion of Convolutional Neural Nets

2024-07-25 · Pirzada Suhail, Amit Sethi

Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about the…

Decision MakingDiversity

Visualizing Random Forest with Self-Organising Map

2014-05-26 · Piotr Płoński, Krzysztof Zaremba

Random Forest (RF) is a powerful ensemble method for classification and regression tasks. It consists of decision trees set. Although, a single tree is well interpretable for human, the ensemble of trees is a black-box m…

ClassificationGeneral Classification