Picture for Yuxian Qiu

Yuxian Qiu

Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training

Sep 22, 2022
Figure 1 for Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Figure 2 for Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Figure 3 for Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Figure 4 for Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Viaarxiv icon

Efficient Activation Quantization via Adaptive Rounding Border for Post-Training Quantization

Add code
Aug 25, 2022
Figure 1 for Efficient Activation Quantization via Adaptive Rounding Border for Post-Training Quantization
Figure 2 for Efficient Activation Quantization via Adaptive Rounding Border for Post-Training Quantization
Figure 3 for Efficient Activation Quantization via Adaptive Rounding Border for Post-Training Quantization
Figure 4 for Efficient Activation Quantization via Adaptive Rounding Border for Post-Training Quantization
Viaarxiv icon

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Add code
Feb 14, 2022
Figure 1 for SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
Figure 2 for SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
Figure 3 for SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
Figure 4 for SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
Viaarxiv icon

Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity

Aug 29, 2020
Figure 1 for Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Figure 2 for Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Figure 3 for Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Figure 4 for Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Viaarxiv icon

Adversarial Defense Through Network Profiling Based Path Extraction

May 09, 2019
Figure 1 for Adversarial Defense Through Network Profiling Based Path Extraction
Figure 2 for Adversarial Defense Through Network Profiling Based Path Extraction
Figure 3 for Adversarial Defense Through Network Profiling Based Path Extraction
Figure 4 for Adversarial Defense Through Network Profiling Based Path Extraction
Viaarxiv icon