Giyoung Jeon — accepted AI-conference papers

2023

Beyond Single Path Integrated Gradients for Reliable Input Attribution via Randomized Path Sampling

Giyoung Jeon, Haedong Jeong, Jaesik Choi

ICCV 2023poster

Input attribution is a widely used explanation method for deep neural networks, especially in visual tasks. Among various attribution methods, Integrated Gradients (IG) is frequently used because of its model-agnostic applicability and desirable axioms. However, previous work has shown that such met…

Cited by 1 PDF ↗Scholar ↗

2022

Distilled Gradient Aggregation: Purify Features for Input Attribution in the Deep Neural Network

Giyoung Jeon, Haedong Jeong, Jaesik Choi

NeurIPS 2022accept

Measuring the attribution of input features toward the model output is one of the popular post-hoc explanations on the Deep Neural Networks (DNNs). Among various approaches to compute the attribution, the gradient-based methods are widely used to generate attributions, because of its ease of impleme…

Cited by 8 Source ↗PDF ↗Scholar ↗