paper-with-me

Papers

DAM: Diffusion Activation Maximization for 3D Global Explanations

2024-01-26 · Hanxiao Tan

In recent years, the performance of point cloud models has been rapidly improved. However, due to the limited amount of relevant explainability studies, the unreliability and opacity of these black-box models may lead to potential risks in applications where human lives are at stake, e.g. autonomous driving or healthcare. This work proposes a DDPM-based point cloud global explainability method (DAM) that leverages Point Diffusion Transformer (PDT), a novel point-wise symmetric model, with dual-classifier guidance to generate high-quality global explanations. In addition, an adapted path gradient integration method for DAM is proposed, which not only provides a global overview of the saliency maps for point cloud categories, but also sheds light on how the attributions of the explanations vary during the generation process. Extensive experiments indicate that our method outperforms existing ones in terms of perceptibility, representativeness, and diversity, with a significant reduction in generation time. Our code is available at: https://github.com/Explain3D/DAM

📄 PDF Abstract BibTeX arXiv:2401.14938

Code (1)

explain3d/dam 공식 구현 pytorch

Tasks

Autonomous DrivingDiversity

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Flow AM: Generating Point Cloud Global Explanations by Latent Alignment

2024-04-29 · Hanxiao Tan

Although point cloud models have gained significant improvements in prediction accuracy over recent years, their trustworthiness is still not sufficiently investigated. In terms of global explainability, Activation Maxim…

Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models

2024-04-03 · Matteo Pennisi, Giovanni Bellitto, Simone Palazzo, Mubarak Shah 외

We present DiffExplainer, a novel framework that, leveraging language-vision models, enables multimodal global explainability. DiffExplainer employs diffusion models conditioned on optimized text prompts, synthesizing im…

DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models

2025-10-16 · Simone Carnemolla, Matteo Pennisi, Sarinda Samarasinghe, Giovanni Bellitto 외 arxiv

Understanding and explaining the behavior of machine learning models is essential for building transparent and trustworthy AI systems. We introduce DEXTER, a data-free framework that employs diffusion models and large la…

LINE: LLM-based Iterative Neuron Explanations for Vision Models

2026-04-09 · Vladimir Zaigrajew, Michał Piechota, Gaspar Sekula, Paweł Gelar 외 arxiv

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods…

DEPICT: Diffusion-Enabled Permutation Importance for Image Classification Tasks

2024-07-19 · Sarah Jabbour, Gregory Kondas, Ella Kazerooni, Michael Sjoding 외

We propose a permutation-based explanation method for image classifiers. Current image-model explanations like activation maps are limited to instance-based explanations in the pixel space, making it difficult to underst…

Feature Importanceimage-classificationImage Classification