paper-with-me

Papers

TraNCE: Transformative Non-linear Concept Explainer for CNNs

2025-03-26 · Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis

Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models looked, concept-based explainability methods provide insights into what the models saw. However, their assumption of linear reconstructability of image activations fails to capture the intricate relationships within these activations. Their Fidelity-only approach to evaluating global explanations also presents a new concern. For the first time, we address these limitations with the novel Transformative Nonlinear Concept Explainer (TraNCE) for CNNs. Unlike linear reconstruction assumptions made by existing methods, TraNCE captures the intricate relationships within the activations. This study presents three original contributions to the CNN explainability literature: (i) An automatic concept discovery mechanism based on variational autoencoders (VAEs). This transformative concept discovery process enhances the identification of meaningful concepts from image activations. (ii) A visualization module that leverages the Bessel function to create a smooth transition between prototypical image pixels, revealing not only what the CNN saw but also what the CNN avoided, thereby mitigating the challenges of concept duplication as documented in previous works. (iii) A new metric, the Faith score, integrates both Coherence and Fidelity for a comprehensive evaluation of explainer faithfulness and consistency.

📄 PDF Abstract BibTeX arXiv:2503.20230

Code (1)

daslimo/trance 공식 구현

Similar Papers 제목 키워드 기반

Concept-based Explanations using Non-negative Concept Activation Vectors and Decision Tree for CNN Models

2022-11-19 · Gayda Mutahar, Tim Miller

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and pe…

Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)

2019-01-21 · Quanshi Zhang, Yu Yang, Ying Nian Wu

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain …

Knowledge DistillationObject

CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization

2020-04-30 · Zijie J. Wang, Robert Turko, Omar Shaikh, Haekyu Park 외

Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understand…

Deep Learning

MCCE: Missingness-aware Causal Concept Explainer

2024-11-14 · Jifan Gao, Guanhua Chen

Causal concept effect estimation is gaining increasing interest in the field of interpretable machine learning. This general approach explains the behaviors of machine learning models by estimating the causal effect of h…

Interpretable Machine Learning

Resolution- and throughput-enhanced spectroscopy using high-throughput computational slit

2016-06-29 · Farnoud Kazemzadeh, Alexander Wong

There exists a fundamental tradeoff between spectral resolution and the efficiency or throughput for all optical spectrometers. The primary factors affecting the spectral resolution and throughput of an optical spectrome…

Vocal Bursts Intensity Prediction