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 …
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 …
of exposures, which is important in image processing, computer graphics, and computer …
Cmua-watermark: A cross-model universal adversarial watermark for combating deepfakes
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 …
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
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 …
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
Event cameras sense intensity changes and have many advantages over conventional
cameras. To take advantage of event cameras, some methods have been proposed to …
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
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 …
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 …
alternatives to classical von Neumann computer architectures. Photonic neural networks …
Boosting lightweight depth estimation via knowledge distillation
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 …
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 …
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
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 …
most of which highly dependent on deep neural networks (DNNs). Recent studies …