Search Results for author:
Found 19 papers, 3 papers with code
MILAN: Masked Image Pretraining on Language Assisted Representation
When the masked autoencoder is pretrained and finetuned on ImageNet-1K dataset with an input resolution of 224x224, MILAN achieves a top-1 accuracy of 85. 4% on ViT-Base, surpassing previous state-of-the-arts by 1%.
CHEX: CHannel EXploration for CNN Model Compression
However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model.
Multi-Dimensional Model Compression of Vision Transformer
In contrast, we advocate a multi-dimensional ViT compression paradigm, and propose to harness the redundancy reduction from attention head, neuron and sequence dimensions jointly.
Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis
We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category.
A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network
In this paper, we have proposed a novel multi-stage training approach that increases diversity in this feature extraction process to make accurate recognition of actions by combining varieties of features extracted from diverse perspectives.
CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans
Moreover, a multi-scale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation.
Privacy Enhancing Machine Learning via Removal of Unwanted Dependencies
The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life.
A Feature-map Discriminant Perspective for Pruning Deep Neural Networks
Network pruning has become the de facto tool to accelerate deep neural networks for mobile and edge applications.
Soft-Root-Sign Activation Function
At present, the most effective and widely-used activation function is ReLU.
Exploiting Operation Importance for Differentiable Neural Architecture Search
All the existing methods determine the importance of each operation directly by architecture weights.
Temporal Action Localization using Long Short-Term Dependency
In the present study, we developed a novel method, referred to as Gemini Network, for effective modeling of temporal structures and achieving high-performance temporal action localization.
Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking
To this end, we propose the cross-scale residual network to exploit scale-related features and the inter-task correlations among the three tasks.
Comb Convolution for Efficient Convolutional Architecture
Convolutional neural networks (CNNs) are inherently suffering from massively redundant computation (FLOPs) due to the dense connection pattern between feature maps and convolution kernels.
Scalable Kernel Learning via the Discriminant Information
Kernel approximation methods create explicit, low-dimensional kernel feature maps to deal with the high computational and memory complexity of standard techniques.
HGC: Hierarchical Group Convolution for Highly Efficient Neural Network
Using this operation, feature maps of different group cannot communicate, which restricts their representation capability.
Supervising Nyström Methods via Negative Margin Support Vector Selection
They approximate explicit, low-dimensional feature mappings for kernel functions from the pairwise comparisons with the training data.
Protecting Genomic Privacy by a Sequence-Similarity Based Obfuscation Method
In the post-genomic era, large-scale personal DNA sequences are produced and collected for genetic medical diagnoses and new drug discovery, which, however, simultaneously poses serious challenges to the protection of personal genomic privacy.
Ratio Utility and Cost Analysis for Privacy Preserving Subspace Projection
With a rapidly increasing number of devices connected to the internet, big data has been applied to various domains of human life.
Efficient Divide-And-Conquer Classification Based on Feature-Space Decomposition
Firstly, we divide the feature space into several subspaces using the decomposition method proposed in this paper.
