paper-with-me

홈 › Papers

Exploring Concept Contribution Spatially: Hidden Layer Interpretation with Spatial Activation Concept Vector

2022-05-21 · Andong Wang, Wei-Ning Lee

To interpret deep learning models, one mainstream is to explore the learned concepts by networks. Testing with Concept Activation Vector (TCAV) presents a powerful tool to quantify the contribution of query concepts (represented by user-defined guidance images) to a target class. For example, we can quantitatively evaluate whether and to what extent concept striped contributes to model prediction zebra with TCAV. Therefore, TCAV whitens the reasoning process of deep networks. And it has been applied to solve practical problems such as diagnosis. However, for some images where the target object only occupies a small fraction of the region, TCAV evaluation may be interfered with by redundant background features because TCAV calculates concept contribution to a target class based on a whole hidden layer. To tackle this problem, based on TCAV, we propose Spatial Activation Concept Vector (SACV) which identifies the relevant spatial locations to the query concept while evaluating their contributions to the model prediction of the target class. Experiment shows that SACV generates a more fine-grained explanation map for a hidden layer and quantifies concepts' contributions spatially. Moreover, it avoids interference from background features. The code is available on https://github.com/AntonotnaWang/Spatial-Activation-Concept-Vector.

📄 PDF Abstract BibTeX arXiv:2205.11511

Code (1)

antonotnawang/spatial-activation-concept-vector 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Causal Interpretation of Neural Network Computations with Contribution Decomposition

2026-03-06 · Joshua Brendan Melander, Zaki Alaoui, Shenghua Liu, Surya Ganguli 외 arxiv

Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activatio…

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

2026-03-02 · Yue Niu, Zhaokai Sun, Jiayi Yang, Xiaofeng Cao 외 arxiv

Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-bo…

Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models

2025-02-27 · CVPR 2025 1 · Itay Benou, Tammy Riklin-Raviv

Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided th…

Zero Shot Segmentation

Layer-Wise Interpretation of Deep Neural Networks Using Identity Initialization

2021-02-26 · Shohei Kubota, Hideaki Hayashi, Tomohiro Hayase, Seiichi Uchida

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random wei…

ClassificationDecision MakingGeneral Classification

Spatial Data Analysis

2024-02-15 · Tobias Rüttenauer

This handbook chapter provides an essential introduction to the field of spatial econometrics, offering a comprehensive overview of techniques and methodologies for analysing spatial data in the social sciences. Spatial …

Econometrics