Search Results for author:
Found 21 papers, 13 papers with code
Positive-Unlabeled Compression on the Cloud
In practice, only a small portion of the original training set is required as positive examples and more useful training examples can be obtained from the massive unlabeled data on the cloud through a PU classifier with an attention based multi-scale feature extractor.
ReNAS:Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
ReNAS: Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
VEGA: Towards an End-to-End Configurable AutoML Pipeline
Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models.
SCOP: Scientific Control for Reliable Neural Network Pruning
To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output.
Learning Frequency Domain Approximation for Binary Neural Networks
Binary neural networks (BNNs) represent original full-precision weights and activations into 1-bit with sign function.
Manifold Regularized Dynamic Network Pruning
Then, the manifold relationship between instances and the pruned sub-networks will be aligned in the training procedure.
Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks
On one hand, massive trainable parameters significantly enhance the performance of these deep networks.
Training Binary Neural Networks through Learning with Noisy Supervision
This paper formalizes the binarization operations over neural networks from a learning perspective.
Full-Stack Filters to Build Minimum Viable CNNs
Existing works used to decrease the number or size of requested convolution filters for a minimum viable CNN on edge devices.
Federated Learning with Positive and Unlabeled Data
We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time.
How Much Demand Flexibility Could Have Spared Texas from the 2021 Outage?
The February 2021 Texas winter power outage has led to hundreds of deaths and billions of dollars in economic losses, largely due to the generation failure and record-breaking electric demand.
BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons
This paper studies the problem of designing compact binary architectures for vision multi-layer perceptrons (MLPs).
A Semi-Supervised Assessor of Neural Architectures
A graph convolutional neural network is introduced to predict the performance of architectures based on the learned representations and their relation modeled by the graph.
DC-NAS: Divide-and-Conquer Neural Architecture Search
Neural architecture searching is a way of automatically exploring optimal deep neural networks in a given huge search space.
Kernel Based Progressive Distillation for Adder Neural Networks
A convolutional neural network (CNN) with the same architecture is simultaneously initialized and trained as a teacher network, features and weights of ANN and CNN will be transformed to a new space to eliminate the accuracy drop.
A Survey on Visual Transformer
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism.
Positive and Unlabeled Federated Learning
We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time.
Source-Free Domain Adaptation via Distribution Estimation
Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different.
A 2030 United States Macro Grid Unlocking Geographical Diversity to Accomplish Clean Energy Goals
Some U. S. states have set clean energy goals and targets in an effort to decarbonize their electricity sectors.
FDViT: Improve the Hierarchical Architecture of Vision Transformer
In this paper, we propose FDViT to improve the hierarchical architecture of the vision transformer by using a flexible downsampling layer that is not limited to integer stride to smoothly reduce the sizes of the middle feature maps.
