Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks

L Wang, KJ Yoon - IEEE transactions on pattern analysis and …, 2021 - ieeexplore.ieee.org
Deep neural models, in recent years, have been successful in almost every field, even
solving the most complex problem statements. However, these models are huge in size with …

Deep learning for hdr imaging: State-of-the-art and future trends

L Wang, KJ Yoon - IEEE transactions on pattern analysis and …, 2021 - ieeexplore.ieee.org
High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range
of exposures, which is important in image processing, computer graphics, and computer …

Cmua-watermark: A cross-model universal adversarial watermark for combating deepfakes

H Huang, Y Wang, Z Chen, Y Zhang, Y Li… - Proceedings of the …, 2022 - ojs.aaai.org
Malicious applications of deepfakes (ie, technologies generating target facial attributes or
entire faces from facial images) have posed a huge threat to individuals' reputation and …

Disrupting deepfakes: Adversarial attacks against conditional image translation networks and facial manipulation systems

N Ruiz, SA Bargal, S Sclaroff - … 2020 Workshops: Glasgow, UK, August 23 …, 2020 - Springer
Face modification systems using deep learning have become increasingly powerful and
accessible. Given images of a person's face, such systems can generate new images of that …

Eventsr: From asynchronous events to image reconstruction, restoration, and super-resolution via end-to-end adversarial learning

L Wang, TK Kim, KJ Yoon - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Event cameras sense intensity changes and have many advantages over conventional
cameras. To take advantage of event cameras, some methods have been proposed to …

Evdistill: Asynchronous events to end-task learning via bidirectional reconstruction-guided cross-modal knowledge distillation

L Wang, Y Chae, SH Yoon, TK Kim… - Proceedings of the …, 2021 - openaccess.thecvf.com
Event cameras sense per-pixel intensity changes and produce asynchronous event streams
with high dynamic range and less motion blur, showing advantages over the conventional …

Developing a photonic hardware platform for brain-inspired computing based on 5× 5 VCSEL arrays

T Heuser, M Pflüger, I Fischer, JA Lott… - Journal of Physics …, 2020 - iopscience.iop.org
Brain-inspired computing concepts like artificial neural networks have become promising
alternatives to classical von Neumann computer architectures. Photonic neural networks …

Boosting lightweight depth estimation via knowledge distillation

J Hu, C Fan, H Jiang, X Guo, Y Gao, X Lu… - … on Knowledge Science …, 2023 - Springer
Monocular depth estimation (MDE) methods are often either too computationally expensive
or not accurate enough due to the trade-off between model complexity and inference …

Semi-supervised student-teacher learning for single image super-resolution

L Wang, KJ Yoon - Pattern Recognition, 2022 - Elsevier
Most existing approaches for single image super-resolution (SISR) resort to quality low-high
resolution (LR-HR) pairs and available degradation kernels to train networks for a specific …

Targeted attention attack on deep learning models in road sign recognition

X Yang, W Liu, S Zhang, W Liu… - IEEE Internet of Things …, 2020 - ieeexplore.ieee.org
Real-world traffic sign recognition is an important step toward building autonomous vehicles,
most of which highly dependent on deep neural networks (DNNs). Recent studies …