Shunxin Wang

4 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird ❓ The Questioner (2)

Venues

CVPR (2) ICCV (1) ICLR (1)

Top co-authors

Nicola Strisciuglio (4) Raymond Veldhuis (2) Decebal Constantin Mocanu (1) Maurice van Keulen (1) Elena Mocanu (1) Qiao Xiao (1) Boqian Wu (1) Christoph Brune (1) Puru Vaish (1) Mykola Pechenizkiy (1)

Research topics

Machine Learning (4) Deep Learning (3) Optimization & Theory · Machine Learning (3) Application Areas (2) Architectures (2) Core Methods (2) Artificial Intelligence (1) Computer Vision (1) Core AI (1) Learning Types (1) Optimization & Theory · Deep Learning (1) Processing (1)

Keywords

image classification (3) neural network (3) frequency shortcut (2) out-of-distribution generalization (2) representation learning (2) model interpretability (1) fourier transform (1) convolutional neural network (1) dynamic sparse training (1) model generalization (1) frequency domain (1) frequency analysis (1) texture pattern (1) dense training (1) adversarial robustness (1) computer vision (1) model robustness (1) data augmentation (1)

Papers

Do ImageNet-trained Models Learn Shortcuts? The Impact of Frequency Shortcuts on Generalization CVPR 2025 Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness ICLR 2025 Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification CVPR 2024 What do neural networks learn in image classification? A frequency shortcut perspective ICCV 2023