Efficient Computing

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle NeurIPS 2019 Adaptive Methods for Nonconvex Optimization NeurIPS 2018 An intriguing failing of convolutional neural networks and the CoordConv solution NeurIPS 2018 ATOMO: Communication-efficient Learning via Atomic Sparsification NeurIPS 2018 Baseline: A Library for Rapid Modeling, Experimentation and Development of Deep Learning Algorithms targeting NLP ACL 2018 Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy CVPR 2018 BlockDrop: Dynamic Inference Paths in Residual Networks CVPR 2018 BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training NeurIPS 2018 ClcNet: Improving the Efficiency of Convolutional Neural Network Using Channel Local Convolutions CVPR 2018 Communication Compression for Decentralized Training NeurIPS 2018 Composing Finite State Transducers on GPUs ACL 2018 CondenseNet: An Efficient DenseNet Using Learned Group Convolutions CVPR 2018 Constructing Fast Network through Deconstruction of Convolution NeurIPS 2018 CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes CVPR 2018 CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++ EMNLP 2018 Deep Neural Networks with Box Convolutions NeurIPS 2018 Deformation Aware Image Compression CVPR 2018 Detail-Preserving Pooling in Deep Networks CVPR 2018 Divide and Conquer for Full-Resolution Light Field Deblurring CVPR 2018 DNN Multimodal Fusion Techniques for Predicting Video Sentiment ACL 2018 Dynamic Video Segmentation Network CVPR 2018 Dynamic Zoom-In Network for Fast Object Detection in Large Images CVPR 2018 Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA CVPR 2018 Efficient Low-rank Multimodal Fusion With Modality-Specific Factors ACL 2018 Efficient Subpixel Refinement With Symbolic Linear Predictors CVPR 2018