知乎 github java_Github标星最多的40篇ICLR2020计算机视觉开源论文合集

编译｜极市平台

转载自|极市平台

1. star:9819｜Weakly Supervised Disentanglement with Guarantees(弱监督学习)

2. star:9819｜Measuring Compositional Generalization: A Comprehensive Method on Realistic Data

3. star:9819｜Meta-Learning without Memorization(元学习/小样本图像分类)

4. star:4977｜U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation(图像翻译/无监督)

5. star:2106｜On the Variance of the Adaptive Learning Rate and Beyond

6. star:1469｜DiffTaichi: Differentiable Programming for Physical Simulation

7. star:1018｜Generative Models for Effective ML on Private, Decentralized Datasets

8. star:963｜Behaviour Suite for Reinforcement Learning(强化学习)

9. star：534｜Contrastive Representation Distillation(知识蒸馏)

10. star：516｜On the Relationship between Self-Attention and Convolutional Layers(注意力机制)

11. star：469｜AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

12. star：443｜NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search(神经网络架构搜索)

13. star：393｜Once for All: Train One Network and Specialize it for Efficient Deployment(神经网络训练)

14. star：246｜BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning(神经网络训练)

15. star：243｜FasterSeg: Searching for Faster Real-time Semantic Segmentation(语义分割)

16. star：213｜Contrastive Learning of Structured World Models

17. star：191｜Real or Not Real, that is the Question(GAN)

18. star：186｜Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving(3D目标检测)

19. star：182｜Learning to Explore using Active Neural SLAM(三维SLAM)

20. star：175｜Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification(行人重识别/无监督)

21. star：132｜AtomNAS: Fine-Grained End-to-End Neural Architecture Search(神经网络架构搜索)

22. star：128｜Strategies for Pre-training Graph Neural Networks(神经网络训练)

23. star117｜Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization(归一化)

24. star：107｜DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

25. star：107｜Neural Arithmetic Units

26. star：106｜Semantically-Guided Representation Learning for Self-Supervised Monocular Depth(单目深度估计)

27. star：100｜Composition-based Multi-Relational Graph Convolutional Networks

28. star：93｜Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation(图像分割/目标检测)

29. star：80｜NAS evaluation is frustratingly hard(神经网络架构搜索)

30. star：74｜Understanding and Robustifying Differentiable Architecture Search(图像分类)

31. star：72｜Fast Neural Network Adaptation via Parameter Remapping and Architecture Search(图像分类/目标检测/语义分割)

32. star：72｜Capsules with Inverted Dot-Product Attention Routing(图像分类)

33. star:53｜Deep Semi-Supervised Anomaly Detection(异常检测)

34. star：51｜Network Deconvolution(图像分类)

35. star：49｜Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning(图像分类)

36. star：36｜A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning(图像分类)

37. star：33｜Empirical Bayes Transductive Meta-Learning with Synthetic Gradients(小样本图像分类/元学习)

38. star：32｜Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings(知识图谱)

39. star：27｜Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps(图像分类)

40. star：22｜Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object Tracking(多目标跟踪)