Search Results for author:
Found 11 papers, 5 papers with code
A Mean Field Ansatz for Zero-Shot Weight Transfer
Specifically, we propose the row-column (RC) ansatz under the mean field point of view, which describes the measure structure of the weights in the neural network (NN) and admits a close measure dynamic.
SAM4UDASS: When SAM Meets Unsupervised Domain Adaptive Semantic Segmentation in Intelligent Vehicles
It involves Semantic-Guided Mask Labeling, which assigns semantic labels to unlabeled SAM masks using UDA pseudo-labels.
Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-making
Simulation is a prospective method for generating diverse and realistic traffic scenarios to aid in the development of driving decision-making systems.
Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
The deep neural network has attained significant efficiency in image recognition.
Application of Machine Learning Methods in Inferring Surface Water Groundwater Exchanges using High Temporal Resolution Temperature Measurements
The results indicate that both ML and DL methods can be used to infer the surface/ground exchange flux.
The Diversity Metrics of Sub-models based on SVD of Jacobians for Ensembles Adversarial Robustness
A new constraints norm is proposed in model training based on these criteria to isolate adversarial transferability without any prior knowledge of adversarial samples.
Dynamic Defense Approach for Adversarial Robustness in Deep Neural Networks via Stochastic Ensemble Smoothed Model
The defense strategies are particularly passive in these processes, and enhancing initiative of such strategies can be an effective way to get out of this arms race.
Distributional Discrepancy: A Metric for Unconditional Text Generation
The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data.
Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation
To alleviate the exposure bias, generative adversarial networks (GAN) use the discriminator to update the generator's parameters directly, but they fail by being evaluated precisely.
The Detection of Distributional Discrepancy for Text Generation
In this paper, we theoretically propose two metric functions to measure the distributional difference between real text and generated text.
Adversarial Sub-sequence for Text Generation
It is easy to improve the existing GAN-based models with this mechanism.
