Edouard Yvinec

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 32

Top Topics

Quantization Error

Top Venues

Publications

Edouard Yvinec, Gabriel Kasser
SPOT: Text Source Prediction from Originality Score Thresholding. CoRR (2024)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
PIPE: Parallelized inference through ensembling of residual quantization expansions. Pattern Recognit. 154 (2024)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings. ICLR (2024)
Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Fighting over-fitting with quantization for learning deep neural networks on noisy labels. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Gradient-Based Post-Training Quantization: Challenging the Status Quo. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
PowerQuant: Automorphism Search for Non-Uniform Quantization. ICLR (2023)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
SPIQ: Data-Free Per-Channel Static Input Quantization. WACV (2023)
Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kévin Bailly
RULe: Relocalization-Uniformization-Landmark Estimation Network for Real-Time Face Alignment in Degraded Conditions. FG (2023)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
REx: Data-Free Residual Quantization Error Expansion. NeurIPS (2023)
Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kévin Bailly
Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction. FG (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Designing strong baselines for ternary neural network quantization through support and mass equalization. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference. CoRR (2023)
Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Fighting Over-Fitting with Quantization for Learning Deep Neural Networks on Noisy Labels. ICIP (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Designing Strong Baselines for Ternary Neural Network Quantization through Support and Mass Equalization. ICIP (2023)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
PowerQuant: Automorphism Search for Non-Uniform Quantization. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions. CoRR (2023)
Rémi Ouazan Reboul, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks. CoRR (2023)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging. IEEE Trans. Pattern Anal. Mach. Intell. 45 (3) (2023)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance. CoRR (2022)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
SPIQ: Data-Free Per-Channel Static Input Quantization. CoRR (2022)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding. CoRR (2022)
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding. IJCAI (2022)
Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Multi-label Transformer for Action Unit Detection. CoRR (2022)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance. NeurIPS (2022)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
REx: Data-Free Residual Quantization Error Expansion. CoRR (2022)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks. CoRR (2021)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks. NeurIPS (2021)
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging. CoRR (2021)
Edouard Yvinec, Arnaud Dapogny, Kévin Bailly
DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation. CoRR (2020)
Edouard Yvinec, Arnaud Dapogny, Kévin Bailly
DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation. FG (2020)