Efficient Computing

A Tensorized Transformer for Language Modeling NeurIPS 2019 A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI AAAI 2019 AutoAssist: A Framework to Accelerate Training of Deep Neural Networks NeurIPS 2019 AutoFocus: Efficient Multi-Scale Inference ICCV 2019 Balanced Sparsity for Efficient DNN Inference on GPU AAAI 2019 Certified Robustness to Adversarial Word Substitutions EMNLP 2019 ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation CVPR 2019 CircConv: A Structured Convolution with Low Complexity AAAI 2019 Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training EMNLP 2019 Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients NeurIPS 2019 CondConv: Conditionally Parameterized Convolutions for Efficient Inference NeurIPS 2019 Constrained deep neural network architecture search for IoT devices accounting for hardware calibration NeurIPS 2019 Coresets for Clustering with Fairness Constraints NeurIPS 2019 Data-driven Estimation of Sinusoid Frequencies NeurIPS 2019 Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation CVPR 2019 Deeper and Wider Siamese Networks for Real-Time Visual Tracking CVPR 2019 Deep Neural Network Quantization via Layer-Wise Optimization Using Limited Training Data AAAI 2019 DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation CVPR 2019 DVC: An End-To-End Deep Video Compression Framework CVPR 2019 E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings NeurIPS 2019 ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model CVPR 2019 Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing AAAI 2019 Efficient Neural Network Compression CVPR 2019 End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization CVPR 2019 Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network CVPR 2019