Search Results for author:
Found 17 papers, 1 papers with code
PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions
However, such techniques suffer from their lack of adaptability to the target devices, as a hardware typically only support specific bit widths.
Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks
To solve this problem, a popular solution is DNN pruning, and more so structured pruning, where coherent computational blocks (e. g. channels for convolutional networks) are removed: as an exhaustive search of the space of pruned sub-models is intractable in practice, channels are typically removed iteratively based on an importance estimation heuristic.
Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
However, this led to an increase in the memory footprint, to a point where it can be challenging to simply load a model on commodity devices such as mobile phones.
Gradient-Based Post-Training Quantization: Challenging the Status Quo
GPTQ essentially consists in learning the rounding operation using a small calibration set.
NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search
However, the optimization of the exponent parameter and weight values remains a challenging and novel problem which could not be solved with previous post training optimization techniques which only learn to round up or down weight values in order to preserve the predictive function.
SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference
In this work, we propose to investigate DNN layer importance, i. e. to estimate the sensitivity of the accuracy w. r. t.
Designing strong baselines for ternary neural network quantization through support and mass equalization
We show experimentally that our approach allows to significantly improve the performance of ternary quantization through a variety of scenarios in DFQ, PTQ and QAT and give strong insights to pave the way for future research in deep neural network quantization.
Fighting over-fitting with quantization for learning deep neural networks on noisy labels
The rising performance of deep neural networks is often empirically attributed to an increase in the available computational power, which allows complex models to be trained upon large amounts of annotated data.
PowerQuant: Automorphism Search for Non-Uniform Quantization
In this paper, we identity the uniformity of the quantization operator as a limitation of existing approaches, and propose a data-free non-uniform method.
SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance
The leap in performance in state-of-the-art computer vision methods is attributed to the development of deep neural networks.
SPIQ: Data-Free Per-Channel Static Input Quantization
Computationally expensive neural networks are ubiquitous in computer vision and solutions for efficient inference have drawn a growing attention in the machine learning community.
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
Batch-Normalization (BN) layers have become fundamental components in the evermore complex deep neural network architectures.
Multi-label Transformer for Action Unit Detection
Action Unit (AU) Detection is the branch of affective computing that aims at recognizing unitary facial muscular movements.
RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks
Deep Neural Networks (DNNs) are ubiquitous in today's computer vision landscape, despite involving considerable computational costs.
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging
Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration.
RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks
Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs.
DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation
In this paper, we introduce a deep, end-to-end trainable ensemble of heatmap-based weak predictors for 2D/3D gaze estimation.
