Search Results for author:
Found 9 papers, 5 papers with code
KirchhoffNet: A Circuit Bridging Message Passing and Continuous-Depth Models
Moreover, we justify that irrespective of the number of parameters within a KirchhoffNet, its forward calculation can always be completed within 1/f seconds, with f representing the hardware's clock frequency.
NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation
In this work, for the first time, a physics-agnostic neural operator-based framework, dubbed NeurOLight, is proposed to learn a family of frequency-domain Maxwell PDEs for ultra-fast parametric photonic device simulation.
Learning from Multiple Annotator Noisy Labels via Sample-wise Label Fusion
Data lies at the core of modern deep learning.
A Simple Data Mixing Prior for Improving Self-Supervised Learning
More notably, our SDMP is the first method that successfully leverages data mixing to improve (rather than hurt) the performance of Vision Transformers in the self-supervised setting.
The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications.
Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularization
Multimodal fusion emerges as an appealing technique to improve model performances on many tasks.
Co-advise: Cross Inductive Bias Distillation
Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks.
Multimodal Knowledge Expansion
The popularity of multimodal sensors and the accessibility of the Internet have brought us a massive amount of unlabeled multimodal data.
Ranked #63 on
Semantic Segmentation
on NYU Depth v2
Projection based Active Gaussian Process Regression for Pareto Front Modeling
A novel projection based active Gaussian process regression (P- aGPR) method is proposed for efficient PF modeling.
