Search Results for author:
Found 13 papers, 5 papers with code
Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement
Recent state-of-the-art (SOTA) UDA methods employ a teacher-student self-training approach, where a teacher model is used to generate pseudo-labels for the new data which in turn guide the training process of the student model.
A Close Look at Spatial Modeling: From Attention to Convolution
Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism.
Test-time Fourier Style Calibration for Domain Generalization
Thus, it is still possible that those methods can overfit to source domains and perform poorly on target domains.
Deep-learned speckle pattern and its application to ghost imaging
Our method, therefore, outperforms the other techniques for ghost imaging, particularly its ability to retrieve high-quality images with extremely low sampling ratios.
0.8% Nyquist computational ghost imaging via non-experimental deep learning
We present a framework for computational ghost imaging based on deep learning and customized pink noise speckle patterns.
Ranked #1 on
Open-Domain Question Answering
on Natural Questions
PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging
Application of deep neural networks to medical imaging tasks has in some sense become commonplace.
Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning
We consider a model-agnostic solution to the problem of Multi-Domain Learning (MDL) for multi-modal applications.
Robust White Matter Hyperintensity Segmentation on Unseen Domain
That is, we train on samples from a set of distributions (sources) and test on samples from a new, unseen distribution (target).
Superresolving second-order correlation imaging using synthesized colored noise speckles
We present a novel method to synthesize non-trivial speckles that can enable superresolving second-order correlation imaging.
Optics Image and Video Processing
Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve
Further, this theory has been well-used in practice.
High order Coherence Functions and Spectral Distributions as given by the Quantum Theory of Laser Radiation
We propose and demonstrate a method for measuring the time evolution of the off-diagonal elements $\rho_{n, n+k}(t)$ of the reduced density matrix obtained from the quantum theory of the laser.
Optics
Learning by Ignoring, with Application to Domain Adaptation
We propose a novel machine learning framework referred to as learning by ignoring (LBI).
Non-invasive imaging of object behind strongly scattering media via cross-spectrum
We develop a method based on the cross-spectrum of an intensity-modulated CW laser, which can extract a signal from an extremely noisy environment and image objects hidden in turbid media.
Optics Biological Physics
