中文
相关论文

相关论文: A Tale of Two Cities: Data and Configuration Varia…

200 篇论文

Robustness of deep neural networks (DNNs) to malicious perturbations is a hot topic in trustworthy AI. Existing techniques obtain robust models given fixed datasets, either by modifying model structures, or by optimizing the process of…

机器学习 · 计算机科学 2022-03-11 Yiqi Zhong , Lei Wu , Xianming Liu , Junjun Jiang

Deep neural networks (DNNs) have recently achieved impressive success across a wide range of real-world vision and language processing tasks, spanning from image classification to many other downstream vision tasks, such as object…

机器学习 · 计算机科学 2025-12-23 Xiangzhong Luo , Di Liu , Hao Kong , Shuo Huai , Hui Chen , Guochu Xiong , Weichen Liu

The success of Deep Neural Networks (DNNs) highly depends on data quality. Moreover, predictive uncertainty makes high performing DNNs risky for real-world deployment. In this paper, we aim to address these two issues by proposing a unified…

机器学习 · 计算机科学 2020-09-28 Krishanu Sarker , Xiulong Yang , Yang Li , Saeid Belkasim , Shihao Ji

Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DNN robustness have been done on images sampled from the same…

机器学习 · 计算机科学 2023-11-08 Kumail Alhamoud , Hasan Abed Al Kader Hammoud , Motasem Alfarra , Bernard Ghanem

It is well-known that deep neural networks (DNNs) have shown remarkable success in many fields. However, when adding an imperceptible magnitude perturbation on the model input, the model performance might get rapid decrease. To address this…

机器学习 · 计算机科学 2022-01-04 Hao Yang , Min Wang , Zhengfei Yu , Yun Zhou

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation and the vision of the Internet-of-Things fuel the interest in resource efficient approaches. These approaches require a carefully…

On-line Precision scalability of the deep neural networks(DNNs) is a critical feature to support accuracy and complexity trade-off during the DNN inference. In this paper, we propose dual-precision DNN that includes two different precision…

机器学习 · 计算机科学 2024-05-14 Jae Hyun Park , Ji Sub Choi , Jong Hwan Ko

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial…

计算机视觉与模式识别 · 计算机科学 2023-09-18 Shaohui Mei , Jiawei Lian , Xiaofei Wang , Yuru Su , Mingyang Ma , Lap-Pui Chau

Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures. However, data seen in the real world are…

机器学习 · 计算机科学 2018-11-26 Muhammad Usama , Dong Eui Chang

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which adversarial training has demonstrated promising results. However,…

机器学习 · 计算机科学 2022-01-25 Hanxun Huang , Yisen Wang , Sarah Monazam Erfani , Quanquan Gu , James Bailey , Xingjun Ma

Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the superior performance of DNNs in these applications, it has…

机器学习 · 计算机科学 2017-08-22 Qinglong Wang , Wenbo Guo , Kaixuan Zhang , Alexander G. Ororbia , Xinyu Xing , Xue Liu , C. Lee Giles

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

计算机视觉与模式识别 · 计算机科学 2023-02-13 Peng Cui , Yang Yue , Zhijie Deng , Jun Zhu

Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now…

机器学习 · 统计学 2017-11-08 Randall Balestriero , Richard Baraniuk

Building robust online content recommendation systems requires learning complex interactions between user preferences and content features. The field has evolved rapidly in recent years from traditional multi-arm bandit and collaborative…

信息检索 · 计算机科学 2018-05-08 Yoel Zeldes , Stavros Theodorakis , Efrat Solodnik , Aviv Rotman , Gil Chamiel , Dan Friedman

Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can be biased toward a…

机器学习 · 计算机科学 2023-03-14 Mahum Naseer , Bharath Srinivas Prabakaran , Osman Hasan , Muhammad Shafique

Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve the training of DNNs. The adoption of an adaptive basis viewpoint of DNNs leads to…

机器学习 · 计算机科学 2019-12-11 Eric C. Cyr , Mamikon A. Gulian , Ravi G. Patel , Mauro Perego , Nathaniel A. Trask

The widespread use of Deep Neural Networks (DNNs) has recently resulted in their application to challenging scientific visualization tasks. While advanced DNNs demonstrate impressive generalization abilities, understanding factors like…

图形学 · 计算机科学 2024-08-13 Atul Kumar , Siddharth Garg , Soumya Dutta

Deep Neural Networks (DNNs) are a critical component for self-driving vehicles. They achieve impressive performance by reaping information from high amounts of labeled data. Yet, the full complexity of the real world cannot be encapsulated…

计算机视觉与模式识别 · 计算机科学 2021-03-26 Julien Rebut , Andrei Bursuc , Patrick Pérez

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this paper, we strive to explore the robust features…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Hong Wang , Yuefan Deng , Shinjae Yoo , Yuewei Lin

This paper integrates deep neural networks (DNNs) into structural economic models to increase flexibility and capture rich heterogeneity while preserving interpretability. Economic structure and machine learning are complements in empirical…

计量经济学 · 经济学 2025-04-28 Max H. Farrell , Tengyuan Liang , Sanjog Misra