computational cost

Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression Interspeech 2023 When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants ACL 2023 Fast Monte-Carlo Approximation of the Attention Mechanism AAAI 2022 Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT ACL 2022 Multilevel Optimization for Inverse Problems COLT 2022 NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models CVPR 2022 Small Footprint Neural Networks for Acoustic Direction of Arrival Estimation Interspeech 2022 Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks ICLR 2022 The Efficiency Misnomer ICLR 2022 3D CNNs With Adaptive Temporal Feature Resolutions CVPR 2021 ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic CVPR 2021 Dynamic Routing Networks WACV 2021 IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers NeurIPS 2021 Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems AAAI 2021 Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling NeurIPS 2021 Rethinking Channel Dimensions for Efficient Model Design CVPR 2021 Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research ICML 2021 Efficient Neural Vision Systems Based on Convolutional Image Acquisition CVPR 2020 Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020 URNet: User-Resizable Residual Networks with Conditional Gating Module AAAI 2020 Dynamic Recursive Neural Network CVPR 2019 Energy and Policy Considerations for Deep Learning in NLP ACL 2019 Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing AAAI 2019 Approximation Algorithms for Cascading Prediction Models ICML 2018 Energy-efficient Amortized Inference with Cascaded Deep Classifiers IJCAI 2018