paper-with-me

홈 › Papers

A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations

2018-05-18 · ICML 2018 7 · Weili Nie, Yang Zhang, Ankit Patel

Backpropagation-based visualizations have been proposed to interpret convolutional neural networks (CNNs), however a theory is missing to justify their behaviors: Guided backpropagation (GBP) and deconvolutional network (DeconvNet) generate more human-interpretable but less class-sensitive visualizations than saliency map. Motivated by this, we develop a theoretical explanation revealing that GBP and DeconvNet are essentially doing (partial) image recovery which is unrelated to the network decisions. Specifically, our analysis shows that the backward ReLU introduced by GBP and DeconvNet, and the local connections in CNNs are the two main causes of compelling visualizations. Extensive experiments are provided that support the theoretical analysis.

📄 PDF Abstract BibTeX arXiv:1805.07039

Code (1)

weilinie/BackpropVis 공식 구현 tf

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective

2025-03-14 · Guanhua Zheng, Jitao Sang, Changsheng Xu

Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability comp…

Decision MakingSensitivity

Towards Predictable Feature Attribution: Revisiting and Improving Guided BackPropagation

2021-09-29 · Guanhua Zheng, Jitao Sang, Wang Haonan, Changsheng Xu

Recently, backpropagation(BP)-based feature attribution methods have been widely adopted to interpret the internal mechanisms of convolutional neural networks (CNNs), and expected to be human-understandable (lucidity) an…

Decision Making

A Rigorous Study Of The Deep Taylor Decomposition

2022-11-14 · Leon Sixt, Tim Landgraf

Saliency methods attempt to explain deep neural networks by highlighting the most salient features of a sample. Some widely used methods are based on a theoretical framework called Deep Taylor Decomposition (DTD), which …

Understanding Individual Decisions of CNNs via Contrastive Backpropagation

2018-12-05 · Jindong Gu, Yinchong Yang, Volker Tresp

A number of backpropagation-based approaches such as DeConvNets, vanilla Gradient Visualization and Guided Backpropagation have been proposed to better understand individual decisions of deep convolutional neural network…

General Classification

Adversarial Examples Are Not Bugs, They Are Superposition

2025-08-24 · Liv Gorton, Owen Lewis arxiv

Adversarial examples -- inputs with imperceptible perturbations that fool neural networks -- remain one of deep learning's most perplexing phenomena despite nearly a decade of research. While numerous defenses and explan…