Výsledky vyhledávání - "Jeong, Yeonjeong"

Report

ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification

Autor: Zhang, Zhibo, Jang, Jongseong, Trabelsi, Chiheb, Li, Ruiwen, Sanner, Scott, Jeong, Yeonjeong, Shim, Dongsub

Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification. However, a key drawback of existing contrastive augmentation methods is that they may lead to the mod

Externí odkaz: http://arxiv.org/abs/2111.14271

Zobrazit plný text záznamu

Report

EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness

Autor: Li, Ruiwen, Zhang, Zhibo, Li, Jiani, Trabelsi, Chiheb, Sanner, Scott, Jang, Jongseong, Jeong, Yeonjeong, Shim, Dongsub

Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which poses a significant challenge

Externí odkaz: http://arxiv.org/abs/2105.14162

Zobrazit plný text záznamu

Report

Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring

Autor: Sattarzadeh, Sam, Sudhakar, Mahesh, Plataniotis, Konstantinos N., Jang, Jongseong, Jeong, Yeonjeong, Kim, Hyunwoo

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides

Externí odkaz: http://arxiv.org/abs/2102.07805

Zobrazit plný text záznamu

Report

Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks

Autor: Sudhakar, Mahesh, Sattarzadeh, Sam, Plataniotis, Konstantinos N., Jang, Jongseong, Jeong, Yeonjeong, Kim, Hyunwoo

Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation, but backpro

Externí odkaz: http://arxiv.org/abs/2102.07799

Zobrazit plný text záznamu

Report

Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation

Autor: Sattarzadeh, Sam, Sudhakar, Mahesh, Lem, Anthony, Mehryar, Shervin, Plataniotis, K. N., Jang, Jongseong, Kim, Hyunwoo, Jeong, Yeonjeong, Lee, Sangmin, Bae, Kyunghoon

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on class activa

Externí odkaz: http://arxiv.org/abs/2010.00672

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation

Autor: Sattarzadeh, Sam, Sudhakar, Mahesh, Lem, Anthony, Mehryar, Shervin, Plataniotis, K. N., Jang, Jongseong, Kim, Hyunwoo, Jeong, Yeonjeong, Lee, Sangmin, Bae, Kyunghoon

Publikováno v: Proceedings of the AAAI Conference on Artificial Intelligence. 35:11639-11647

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::025e3ff2115ef26e8643243d717310bb
https://doi.org/10.1609/aaai.v35i13.17384

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání