Search Results for author:
Found 23 papers, 12 papers with code
Ultrasound Lung Aeration Map via Physics-Aware Neural Operators
Lung ultrasound is a growing modality in clinics for diagnosing and monitoring acute and chronic lung diseases due to its low cost and accessibility.
Open Vocabulary Monocular 3D Object Detection
In this work, we pioneer the study of open-vocabulary monocular 3D object detection, a novel task that aims to detect and localize objects in 3D space from a single RGB image without limiting detection to a predefined set of categories.
Multi-Modal Self-Supervised Learning for Surgical Feedback Effectiveness Assessment
Creating such an automated system poses challenges, as it requires an understanding of both the verbal feedback delivered by the trainer and the visual context of the real-time surgical scene.
A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
Our unified model offers a versatile solution for MRI, adapting seamlessly to various measurement undersampling and imaging resolutions, making it highly effective for flexible and reliable clinical imaging.
Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis
Accurate diagnosis of ocular surface diseases is critical in optometry and ophthalmology, which hinge on integrating clinical data sources (e. g., meibography imaging and clinical metadata).
Beyond Closure Models: Learning Chaotic-Systems via Physics-Informed Neural Operators
We propose an alternative end-to-end learning approach using a physics-informed neural operator (PINO) that overcomes this limitation by not using a closure model or a coarse-grid solver.
Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization
Learning visual features from unlabeled images has proven successful for semantic categorization, often by mapping different $views$ of the same object to the same feature to achieve recognition invariance.
Deep Multimodal Fusion for Surgical Feedback Classification
This work offers an important first look at the feasibility of automated classification of real-world live surgical feedback based on text, audio, and video modalities.
Tracking the Dynamics of the Tear Film Lipid Layer
Tear film instability is a known factor for DED, and is thought to be regulated in large part by the thin lipid layer that covers and stabilizes the tear film.
Unsupervised Scene Sketch to Photo Synthesis
Taking this advantage, we synthesize a photo-realistic image by combining the structure of a sketch and the visual style of a reference photo.
Open Long-Tailed Recognition in a Dynamic World
A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes).
Compact and Optimal Deep Learning with Recurrent Parameter Generators
We propose a drastically different approach to compact and optimal deep learning: We decouple the Degrees of freedom (DoF) and the actual number of parameters of a model, optimize a small DoF with predefined random linear constraints for a large model of arbitrary architecture, in one-stage end-to-end learning.
Ranked #97 on
Image Classification
on ObjectNet
(using extra training data)
Language-Guided Global Image Editing via Cross-Modal Cyclic Mechanism
Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset.
3D Shape Reconstruction from Free-Hand Sketches
Additionally, we propose a sketch standardization module to handle different sketch distortions and styles.
A Deep Learning Approach for Meibomian Gland Atrophy Evaluation in Meibography Images
The development set was used to train and tune the deep learning model, while the evaluation set was used to evaluate the performance of the model.
Orthogonal Convolutional Neural Networks
We develop an efficient approach to impose filter orthogonality on a convolutional layer based on the doubly block-Toeplitz matrix representation of the convolutional kernel instead of using the common kernel orthogonality approach, which we show is only necessary but not sufficient for ensuring orthogonal convolutions.
Learning Coupled Spatial-temporal Attention for Skeleton-based Action Recognition
In this paper, we propose a coupled spatial-temporal attention (CSTA) model for skeleton-based action recognition, which aims to figure out the most discriminative joints and frames in spatial and temporal domains simultaneously.
Spatial Transformer for 3D Point Clouds
We propose a novel end-to-end approach to learn different non-rigid transformations of the input point cloud so that optimal local neighborhoods can be adopted at each layer.
SurReal: Fréchet Mean and Distance Transform for Complex-Valued Deep Learning
On RadioML, our model achieves comparable RF modulation classification accuracy at 10% of the baseline model size.
Large-Scale Long-Tailed Recognition in an Open World
We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes.
Successive Embedding and Classification Loss for Aerial Image Classification
To address the overfitting problem in aerial image classification, we consider the neural network as successive transformations of an input image into embedded feature representations and ultimately into a semantic class label, and train neural networks to optimize image representations in the embedded space in addition to optimizing the final classification score.
Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
In this paper, we present a novel deep ranking model with feature learning and fusion by learning a large adaptive margin between the intra-class distance and inter-class distance to solve the person re-identification problem.
Point to Set Similarity Based Deep Feature Learning for Person Re-Identification
One of the key issues for deep learning based person Re-ID is the selection of proper similarity comparison criteria, and the performance of learned features using existing criterion based on pairwise similarity is still limited, because only P2P distances are mostly considered.
