Search Results for author:
Found 7 papers, 2 papers with code
SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation
These findings demonstrate that our method exhibits strong performance in PE segmentation tasks, potentially enhancing the accuracy of automatic segmentation of PE and providing a powerful diagnostic tool for clinical physicians.
Triadic Temporal Exponential Random Graph Models (TTERGM)
Temporal exponential random graph models (TERGM) are powerful statistical models that can be used to infer the temporal pattern of edge formation and elimination in complex networks (e. g., social networks).
Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block
Recently, massive architectures based on Convolutional Neural Network (CNN) and self-attention mechanisms have become necessary for audio classification.
Ranked #3 on
Environmental Sound Classification
on UrbanSound8K
(Accuracy metric)
Stingy Teacher: Sparse Logits Suffice to Fail Knowledge Distillation
However, it is unclear why the distorted distribution of the logits is catastrophic to the student model.
Tracking Fast Neural Adaptation by Globally Adaptive Point Process Estimation for Brain-Machine Interface
In order to identify the active neurons in brain control and track their tuning property changes, we propose a globally adaptive point process method (GaPP) to estimate the neural modulation state from spike trains, decompose the states into the hyper preferred direction and reconstruct the kinematics in a dual-model framework.
Signature of multilayer graphene strain-controlled domain walls in quantum Hall effect
Reversible and controlled uniaxial strain triggers these topological defects, manifested as new quantum Hall effect plateaus as well as a discrete and reversible modulation of the current across the device.
Mesoscale and Nanoscale Physics
Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results
On the possibility side, we show that it is still feasible to construct adversarial training methods to significantly improve the resilience of networks against adversarial inputs over empirical datasets.
