Search Results for author:
Found 15 papers, 6 papers with code
Integrated Steganography and Steganalysis with Generative Adversarial Networks
The discriminative model simulate the steganalysis process, which can help us understand the sensitivity of cover images to semantic changes.
Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioning
In this paper, we provide a thorough study on an effective integration of HFL and VFL, to achieve communication efficiency and overcome the above limitations when data is both horizontally and vertically partitioned.
Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, followed by the sparsity score evaluation according to the target sparsity constraint.
Enhanced Sparsification via Stimulative Training
To alleviate this issue, we first study and reveal the relative sparsity effect in emerging stimulative training and then propose a structured pruning framework, named STP, based on an enhanced sparsification paradigm which maintains the magnitude of dropped weights and enhances the expressivity of kept weights by self-distillation.
MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
To this end, we propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs.
Efficient Architecture Search via Bi-level Data Pruning
Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention.
SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution
Therefore, we propose a sparse baseline of VOS named SpVOS in this work, which develops a novel triple sparse convolution to reduce the computation costs of the overall VOS framework.
Boosting Residual Networks with Group Knowledge
Specifically, we implicitly divide all subnets into hierarchical groups by subnet-in-subnet sampling, aggregate the knowledge of different subnets in each group during training, and exploit upper-level group knowledge to supervise lower-level subnet groups.
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization
Moreover, GPUSQ-ViT can boost actual deployment performance by 1. 39-1. 79 times and 3. 22-3. 43 times of latency and throughput on A100 GPU, and 1. 57-1. 69 times and 2. 11-2. 51 times improvement of latency and throughput on AGX Orin.
Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend
Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior.
Channel Permutations for N:M Sparsity
We introduce channel permutations as a method to maximize the accuracy of N:M sparse networks.
Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner
With the development of deep learning, neural networks tend to be deeper and larger to achieve good performance.
Accelerating Sparse Deep Neural Networks
We present the design and behavior of Sparse Tensor Cores, which exploit a 2:4 (50%) sparsity pattern that leads to twice the math throughput of dense matrix units.
Self-Supervised Generative Adversarial Compression
Deep learning’s success has led to larger and larger models to handle more and more complex tasks; trained models often contain millions of parameters.
Self-Supervised GAN Compression
Deep learning's success has led to larger and larger models to handle more and more complex tasks; trained models can contain millions of parameters.
