← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

URNet: User-Resizable Residual Networks with Conditional Gating Module AAAI 2020
Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks AAAI 2020
Adversarially Robust Distillation AAAI 2020
InstaNAS: Instance-Aware Neural Architecture Search AAAI 2020
Information-Theoretic Understanding of Population Risk Improvement with Model Compression AAAI 2020
Few Shot Network Compression via Cross Distillation AAAI 2020
Indirect Stochastic Gradient Quantization and Its Application in Distributed Deep Learning AAAI 2020
MoBiNet: A Mobile Binary Network for Image Classification WACV 2020
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection WACV 2020
TKD: Temporal Knowledge Distillation for Active Perception WACV 2020
Wide Hidden Expansion Layer for Deep Convolutional Neural Networks WACV 2020
Accuracy Booster: Performance Boosting using Feature Map Re-calibration WACV 2020
Regularize, Expand and Compress: NonExpansive Continual Learning WACV 2020
Leveraging Filter Correlations for Deep Model Compression WACV 2020
Local Binary Pattern Networks WACV 2020
ASAP: Architecture Search, Anneal and Prune AISTATS 2020
Contrastive Distillation on Intermediate Representations for Language Model Compression EMNLP 2020
TernaryBERT: Distillation-aware Ultra-low Bit BERT EMNLP 2020
On the Sparsity of Neural Machine Translation Models EMNLP 2020
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models EMNLP 2020
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance EMNLP 2020
When BERT Plays the Lottery, All Tickets Are Winning EMNLP 2020
Monolingual Adapters for Zero-Shot Neural Machine Translation EMNLP 2020
An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training EMNLP 2020
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing EMNLP 2020