Search Results for author:
Found 18 papers, 1 papers with code
Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data
Automated knee cartilage segmentation using point-of-care ultrasound devices and deep-learning networks has the potential to enhance the management of knee osteoarthritis.
Re-visiting Skip-Gram Negative Sampling: Dimension Regularization for More Efficient Dissimilarity Preservation in Graph Embeddings
In this work, we show that node-wise repulsion is, in aggregate, an approximate re-centering of the node embedding dimensions.
DT/MARS-CycleGAN: Improved Object Detection for MARS Phenotyping Robot
This work specifically tackles the first challenge by proposing a novel Digital-Twin(DT)MARS-CycleGAN model for image augmentation to improve our Modular Agricultural Robotic System (MARS)'s crop object detection from complex and variable backgrounds.
When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendations
The first negatively impacts less popular items, due to the fact that less popular items rely on trailing latent components to recover their values.
Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification
With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern.
MMViT: Multiscale Multiview Vision Transformers
Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel.
Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer
Conclusion: A patient-specific vision-transformer-based network was developed and shown to be accurate and efficient to reconstruct 3D CT images from kV images.
Core-Periphery Principle Guided Redesign of Self-Attention in Transformers
Designing more efficient, reliable, and explainable neural network architectures is critical to studies that are based on artificial intelligence (AI) techniques.
Coupling Artificial Neurons in BERT and Biological Neurons in the Human Brain
Linking computational natural language processing (NLP) models and neural responses to language in the human brain on the one hand facilitates the effort towards disentangling the neural representations underpinning language perception, on the other hand provides neurolinguistics evidence to evaluate and improve NLP models.
normflows: A PyTorch Package for Normalizing Flows
It allows to build normalizing flow models from a suite of base distributions, flow layers, and neural networks.
Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning
To address this problem, we propose to infuse human experts' intelligence and domain knowledge into the training of deep neural networks.
A universal probabilistic spike count model reveals ongoing modulation of neural variability
We find that variability in these cells defies a simple parametric relationship with mean spike count as assumed in standard models, its modulation by external covariates can be comparably strong to that of the mean firing rate, and slow low-dimensional latent factors explain away neural correlations.
RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity
We present RAWLSNET, a system for altering Bayesian Network (BN) models to satisfy the Rawlsian principle of fair equality of opportunity (FEO).
Feature-Align Network with Knowledge Distillation for Efficient Denoising
(2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss.
Evolving Antennas for Ultra-High Energy Neutrino Detection
Evolutionary algorithms borrow from biology the concepts of mutation and selection in order to evolve optimized solutions to known problems.
Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization
In this paper, we propose an automatic and fast algorithm to localize and label the vertebra centroids in 3D CT volumes.
Human Curation and Convnets: Powering Item-to-Item Recommendations on Pinterest
This paper presents Pinterest Related Pins, an item-to-item recommendation system that combines collaborative filtering with content-based ranking.
Visual Search at Pinterest
We demonstrate that, with the availability of distributed computation platforms such as Amazon Web Services and open-source tools, it is possible for a small engineering team to build, launch and maintain a cost-effective, large-scale visual search system with widely available tools.
