爱可可老师一周论文精选(2019.5.11)

No 1. 【比MobileNetV2快2倍更准确的MobileNetV3】
No 2. 《Survey of Dropout Methods for Deep Neural Networks》
No 3. 《Low-Memory Neural Network Training: A Technical Report》
No 4. 《A Survey on Neural Architecture Search》
No 5. 《Graph Matching Networks for Learning the Similarity of Graph Structured Objects》
No 6. 《Unified Language Model Pre-training for Natural Language Understanding and Generation》
No 7. 【深度学习蛋白质序列标注与功能预测】
No 8. 《Adversarial Examples Are Not Bugs, They Are Features》
No 9. 【Few-Shot无监督图到图变换:从少量样本挖掘新事物特质】
No 10. 《WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving》
No 11. 《Billion-scale semi-supervised learning for image classification》
No 12. 《The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks》
No 13. 《Self-supervised Learning for Video Correspondence Flow》
No 14. 《Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks》
No 15. 《HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection》
No 16. 《Deep Learning for Audio Signal Processing》
No 17. 《Bayesian Optimization using Deep Gaussian Processes》
No 18. 《Convolutional Mesh Regression for Single-Image Human Shape Reconstruction》
No 19. 《FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance》
No 20. 《Meta-learning of Sequential Strategies》
No 21. 《GAN Augmented Text Anomaly Detection with Sequences of Deep Statistics》
No 22. 《ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning》
No 23. 《Self-Supervised Convolutional Subspace Clustering Network》
No 24. 《Full-Jacobian Representation of Neural Networks》
No 25. 《Estimating Kullback-Leibler Divergence Using Kernel Machines》
No 26. 《Reducing Anomaly Detection in Images to Detection in Noise》
No 27. 《26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone》
No 28. 《Challenges of Real-World Reinforcement Learning》
No 29. 《Controllable Artistic Text Style Transfer via Shape-Matching GAN》
No 30. 《3D BAT: A Semi-Automatic, Web-based 3D Annotation Toolbox for Full-Surround, Multi-Modal Data Streams》

发表评论

电子邮件地址不会被公开。 必填项已用*标注