Probvlm: Probabilistic adapter for frozen vison-language models
Large-scale vision-language models (VLMs) like CLIP successfully find correspondences
between images and text. Through the standard deterministic mapping process, an image or …
between images and text. Through the standard deterministic mapping process, an image or …
Bayescap: Bayesian identity cap for calibrated uncertainty in frozen neural networks
High-quality calibrated uncertainty estimates are crucial for numerous real-world
applications, especially for deep learning-based deployed ML systems. While Bayesian …
applications, especially for deep learning-based deployed ML systems. While Bayesian …
Calibrating multimodal learning
Multimodal machine learning has achieved remarkable progress in a wide range of
scenarios. However, the reliability of multimodal learning remains largely unexplored. In this …
scenarios. However, the reliability of multimodal learning remains largely unexplored. In this …
MSE-Fusion: Weakly supervised medical image fusion with modal synthesis and enhancement
L Wang, Y Liu, J Mi, J Zhang - Engineering Applications of Artificial …, 2023 - Elsevier
Existing multi-modal image fusion methods utilize multi-modal images as input that require
multiple imaging of patients causing harm to patients' bodies and large costs, moreover …
multiple imaging of patients causing harm to patients' bodies and large costs, moreover …
History-enhanced and Uncertainty-aware Trajectory Recovery via Attentive Neural Network
A considerable amount of mobility data has been accumulated due to the proliferation of
location-based services. Nevertheless, compared with mobility data from transportation …
location-based services. Nevertheless, compared with mobility data from transportation …
Uncertainty-guided progressive GANs for medical image translation
Image-to-image translation plays a vital role in tackling various medical imaging tasks such
as attenuation correction, motion correction, undersampled reconstruction, and denoising …
as attenuation correction, motion correction, undersampled reconstruction, and denoising …
Uncertainty aware neural network from similarity and sensitivity
Recent uncertainty quantification approaches lack transparency. Algorithms often perform
poorly in an input domain and the reason for poor performance remains unknown …
poorly in an input domain and the reason for poor performance remains unknown …
Unsupervised joint image transfer and uncertainty quantification using patch invariant networks
Unsupervised image transfer enables intra-and inter-modality image translation in
applications where a large amount of paired training data is not abundant. To ensure a …
applications where a large amount of paired training data is not abundant. To ensure a …
Video frame interpolation with learnable uncertainty and decomposition
Z Yu, X Chen, S Ren - IEEE Signal Processing Letters, 2022 - ieeexplore.ieee.org
Video frame interpolation can flexibly increase the temporal resolution of low frame-rate
videos by generating the missing intermediate frames at any time. Existing methods …
videos by generating the missing intermediate frames at any time. Existing methods …
Usim-dal: Uncertainty-aware statistical image modeling-based dense active learning for super-resolution
Dense regression is a widely used approach in computer vision for tasks such as image
super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation …
super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation …