parameter efficiency

DeLighT: Deep and Light-weight Transformer ICLR 2021 Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset ICML 2021 DTMNet: A Discrete Tchebichef Moments-Based Deep Neural Network for Multi-Focus Image Fusion ICCV 2021 Efficient Equivariant Network NeurIPS 2021 Efficient Feature Transformations for Discriminative and Generative Continual Learning CVPR 2021 Efficient Generalized Spherical CNNs ICLR 2021 EfficientNetV2: Smaller Models and Faster Training ICML 2021 Efficient Weight Factorization for Multilingual Speech Recognition Interspeech 2021 Extremely Low Footprint End-to-End ASR System for Smart Device Interspeech 2021 FP-NAS: Fast Probabilistic Neural Architecture Search CVPR 2021 HyperGrid Transformers: Towards A Single Model for Multiple Tasks ICLR 2021 Importance-based Neuron Allocation for Multilingual Neural Machine Translation ACL 2021 Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning ACL 2021 It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners NAACL 2021 LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search CVPR 2021 Lightweight Adapter Tuning for Multilingual Speech Translation ACL 2021 Multilingual Speech Translation from Efficient Finetuning of Pretrained Models ACL 2021 Multi-Path Neural Networks for On-Device Multi-Domain Visual Classification WACV 2021 Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects NAACL 2021 Optimizing Reusable Knowledge for Continual Learning via Metalearning NeurIPS 2021 Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection Interspeech 2021 PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs AAAI 2021 Pruning Randomly Initialized Neural Networks with Iterative Randomization NeurIPS 2021 Revisiting Dynamic Convolution via Matrix Decomposition ICLR 2021 Scaling Local Self-Attention for Parameter Efficient Visual Backbones CVPR 2021