Search Results for author:
Found 21 papers, 8 papers with code
Learning to Detect Open Classes for Universal Domain Adaptation
The new transferability measure accurately quantifies the inclination of a target example to the open classes.
Ranked #8 on
Universal Domain Adaptation
on DomainNet
CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening
We aim to assist image-based myopia screening by resolving two longstanding problems, "how to integrate the information of ocular images of a pair of eyes" and "how to incorporate the inherent dependence among high-myopia status and axial length for both eyes."
AdaptLIL: A Gaze-Adaptive Visualization for Ontology Mapping
This paper showcases AdaptLIL, a real-time adaptive link-indented list ontology mapping visualization that uses eye gaze as the primary input source.
Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement
In order to achieve superior preliminary brightness enhancement by optimally integrating spatial channel information with low-frequency components in the wavelet transform, we introduce channel-wise Mamba, which compensates for the long-range dependencies of CNNs and has lower complexity compared to Diffusion and Transformer models.
Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
TRON comprises two main components: (1) a novel conformal score to sample response sets of minimum size, and (2) a nonconformity score to identify high-quality responses based on self-consistency theory, controlling the error rates by two specific risk levels.
Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology
Our VLSA could pave a new way for SA in CPATH by offering weakly-supervised MIL an effective means to learn valuable prognostic clues from gigapixel WSIs.
OU-CoViT: Copula-Enhanced Bi-Channel Multi-Task Vision Transformers with Dual Adaptation for OU-UWF Images
Furthermore, the novel architecture of OU-CoViT allows generalizability and extensions of our dual adaptation and Copula Loss to various ViT variants and large DL models on small medical datasets.
Why Misinformation is Created? Detecting them by Integrating Intent Features
Accordingly, we propose to reason the intent of articles and form the corresponding intent features to promote the veracity discrimination of article features.
OUCopula: Bi-Channel Multi-Label Copula-Enhanced Adapter-Based CNN for Myopia Screening Based on OU-UWF Images
Inspired by the complex relationships between OU and the high correlation between the (continuous) outcome labels (Spherical Equivalent and Axial Length), we propose a framework of copula-enhanced adapter convolutional neural network (CNN) learning with OU UWF fundus images (OUCopula) for joint prediction of multiple clinical scores.
CeCNN: Copula-enhanced convolutional neural networks in joint prediction of refraction error and axial length based on ultra-widefield fundus images
The CeCNN formulates a multiresponse regression that relates multiple dependent discrete-continuous responses and the image covariate, where the nonlinearity of the association is modeled by a backbone CNN.
AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images
To tackle these problems, we propose a novel adversarial multiple instance learning (AdvMIL) framework.
DSCA: A Dual-Stream Network with Cross-Attention on Whole-Slide Image Pyramids for Cancer Prognosis
Our experiments and ablation studies verify that (i) the proposed DSCA could outperform existing state-of-the-art methods in cancer prognosis, by an average C-Index improvement of around 4. 6%; (ii) our DSCA network is more efficient in computation -- it has more learnable parameters (6. 31M vs. 860. 18K) but less computational costs (2. 51G vs. 4. 94G), compared to a typical existing multi-resolution network.
Transferable Query Selection for Active Domain Adaptation
Due to the domain shift, the query selection criteria of prior active learning methods may be ineffective to select the most informative target samples for annotation.
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
Before sufficient training data is available, fine-tuning neural networks pre-trained on large-scale datasets substantially outperforms training from random initialization.
Low-Power Computer Vision: Status, Challenges, Opportunities
In addition to mobile phones, many autonomous systems rely on visual data for making decisions and some of these systems have limited energy (such as unmanned aerial vehicles also called drones and mobile robots).
Physics Enhanced Artificial Intelligence
We propose that intelligently combining models from the domains of Artificial Intelligence or Machine Learning with Physical and Expert models will yield a more "trustworthy" model than any one model from a single domain, given a complex and narrow enough problem.
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing. ieee. org/lpirc) is an annual competition started in 2015.
A salt and pepper noise image denoising method based on the generative classification
In this paper, an image denoising algorithm is proposed for salt and pepper noise.
Integrating Topic Modeling with Word Embeddings by Mixtures of vMFs
Gaussian LDA integrates topic modeling with word embeddings by replacing discrete topic distribution over word types with multivariate Gaussian distribution on the embedding space.
Quality Dynamic Human Body Modeling Using a Single Low-cost Depth Camera
In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor.
Data-driven Flower Petal Modeling with Botany Priors
Each segmented petal is then fitted with a scale-invariant morphable petal shape model, which is constructed from individually scanned exemplar petals.
