Picture for Kevin Bailly

Kevin Bailly

PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions

Add code
Nov 27, 2023
Viaarxiv icon

Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks

Add code
Nov 17, 2023
Viaarxiv icon

Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings

Add code
Sep 29, 2023
Viaarxiv icon

MultIOD: Rehearsal-free Multihead Incremental Object Detector

Add code
Sep 11, 2023
Viaarxiv icon

Gradient-Based Post-Training Quantization: Challenging the Status Quo

Add code
Aug 15, 2023
Viaarxiv icon

NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search

Add code
Aug 10, 2023
Viaarxiv icon

SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference

Add code
Aug 09, 2023
Viaarxiv icon

Designing strong baselines for ternary neural network quantization through support and mass equalization

Add code
Jun 30, 2023
Viaarxiv icon

Fighting over-fitting with quantization for learning deep neural networks on noisy labels

Add code
Mar 21, 2023
Viaarxiv icon

Fighting noise and imbalance in Action Unit detection problems

Add code
Mar 06, 2023
Viaarxiv icon