Results 71 to 80 of about 219,753 (266)

Solid Harmonic Wavelet Bispectrum for Image Analysis

Advanced Science, EarlyView.
The Solid Harmonic Wavelet Bispectrum (SHWB), a rotation‐ and translation‐invariant descriptor that captures higher‐order (phase) correlations in signals, is introduced. Combining wavelet scattering, bispectral analysis, and group theory, SHWB achieves interpretable, data‐efficient representations and demonstrates competitive performance across texture,
Alex Brown, Mathilda Avirett‐Mackenzie, Carolin Villforth, Georgios Exarchakis   +3 more
wiley   +1 more source

Imbalanced Adversarial Training with Reweighting

2022 IEEE International Conference on Data Mining (ICDM), 2022
Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks. However, almost all existing studies about adversarial training are focused on balanced datasets, where each class has an equal amount of training examples.
Wentao Wang 0006, Han Xu 0002, Xiaorui Liu, Yaxin Li 0001, Bhavani Thuraisingham, Jiliang Tang   +5 more
openaire   +2 more sources

Learnable Diffusion Framework for Mouse V1 Neural Decoding

Advanced Science, EarlyView.
We introduce Sensorium‐Viz, a diffusion‐based framework for reconstructing high‐fidelity visual stimuli from mouse primary visual cortex activity. By integrating a novel spatial embedding module with a Diffusion Transformer (DiT) and a synthetic‐response augmentation strategy, our model outperforms state‐of‐the‐art fMRI‐based baselines, enabling robust
Kaiwen Deng, Peter S. Schwendeman, Yuanfang Guan   +2 more
wiley   +1 more source

Strength-Adaptive Adversarial Training

CoRR, 2022
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness ...
Chaojian Yu, Dawei Zhou 0004, Li Shen 0008, Jun Yu 0001, Bo Han 0003, Mingming Gong, Nannan Wang 0001, Tongliang Liu   +7 more
openaire   +2 more sources

Atomic Defects in Layered Transition Metal Dichalcogenides for Sustainable Energy Storage and the Intelligent Trends in Data Analytics

Advanced Science, EarlyView.
This review comprehensively summarizes the atomic defects in TMDs for their applications in sustainable energy storage devices, along with the latest progress in ML methodologies for high‐throughput TEM data analysis, offering insights on how ML‐empowered microscopy facilitates bridging structure–property correlation and inspires knowledge for precise ...
Zheng Luo, Ying Yang, Zizhen Fu, Fengqi Liu, Susu Fang, Kele Xu, Shanshan Wang   +6 more
wiley   +1 more source

Diffusion–Model–Driven Discovery of Ferroelectrics for Photocurrent Applications

Advanced Science, EarlyView.
We developed a diffusion model–based generative AI and high‐throughput screening framework that accelerates the discovery of photovoltaic ferroelectrics. By coupling AI driven crystal generation with machine learning and DFT screening, we identified Ca3P2 and LiCdP as new ferroelectric materials exhibiting strong polarization, feasible switching ...
Byung Chul Yeo, Hyun‐Jae Lee, Sungwoo Kang, Jung‐Hoon Lee   +3 more
wiley   +1 more source

Three-Dimensional Reconstruction Pre-Training as a Prior to Improve Robustness to Adversarial Attacks and Spurious Correlation

Entropy
Ensuring robustness of image classifiers against adversarial attacks and spurious correlation has been challenging. One of the most effective methods for adversarial robustness is a type of data augmentation that uses adversarial examples during training.
Yutaro Yamada, Fred Weiying Zhang, Yuval Kluger, Ilker Yildirim   +3 more
doaj   +1 more source

MixUp as Directional Adversarial Training

CoRR, 2019
In this work, we explain the working mechanism of MixUp in terms of adversarial training. We introduce a new class of adversarial training schemes, which we refer to as directional adversarial training, or DAT. In a nutshell, a DAT scheme perturbs a training example in the direction of another example but keeps its original label as the training target.
Guillaume P. Archambault, Yongyi Mao, Hongyu Guo, Richong Zhang   +3 more
openaire   +2 more sources

Semantics-Preserving Adversarial Training

CoRR, 2020
Preprint.
Wonseok Lee 0001, Hanbit Lee, Sang-goo Lee   +2 more
openaire   +2 more sources

Multimodal Wearable Biosensing Meets Multidomain AI: A Pathway to Decentralized Healthcare

Advanced Science, EarlyView.
Multimodal biosensing meets multidomain AI. Wearable biosensors capture complementary biochemical and physiological signals, while cross‐device, population‐aware learning aligns noisy, heterogeneous streams. This Review distills key sensing modalities, fusion and calibration strategies, and privacy‐preserving deployment pathways that transform ...
Chenshu Liu, Haolin Fan, Minwoo Kim, Tong Zhou, Pinyi Yang, Lingdi Zhao, Yiran Wang, Ziyuan Che, Chia‐Wei Liu, Bingbing Li, Yangzhi Zhu   +10 more
wiley   +1 more source