Search Results for author:
Found 9 papers, 1 papers with code
Generating Multi-Center Classifier via Conditional Gaussian Distribution
Specifically, we create a conditional Gaussian distribution for each class and then sample multiple sub-centers from that distribution to extend the linear classifier.
Vision Big Bird: Random Sparsification for Full Attention
Inspired by one of the most successful transformers-based models for NLP: Big Bird, we propose a novel sparse attention mechanism for Vision Transformers (ViT).
RSIR Transformer: Hierarchical Vision Transformer using Random Sampling Windows and Important Region Windows
Recently, Transformers have shown promising performance in various vision tasks.
Axially Expanded Windows for Local-Global Interaction in Vision Transformers
Recently, Transformers have shown promising performance in various vision tasks.
Self-Supervised Implicit Attention: Guided Attention by The Model Itself
To verify the effectiveness of SSIA, we performed a particular implementation (called an SSIA block) in convolutional neural network models and validated it on several image classification datasets.
Positional Label for Self-Supervised Vision Transformer
Positional encoding is important for vision transformer (ViT) to capture the spatial structure of the input image.
ReplaceBlock: An improved regularization method based on background information
In this way, ReplaceBlock can effectively simulate the feature map of the occluded image.
The Fixed Sub-Center: A Better Way to Capture Data Complexity
The F-SC specifically, first samples a class center Ui for each class from a uniform distribution, and then generates a normal distribution for each class, where the mean is equal to Ui.
Layerwise Recurrent Autoencoder for General Real-world Traffic Flow Forecasting
To forecast the traffic flow across a wide area and overcome the mentioned challenges, we design and propose a promising forecasting model called Layerwise Recurrent Autoencoder (LRA), in which a three-layer stacked autoencoder (SAE) architecture is used to obtain temporal traffic correlations and a recurrent neural networks (RNNs) model for prediction.
