最高一万星!GitHub 标星最多的 40 篇 ICLR2020 计算机视觉论文合集,附打包下载

编译|极市平台

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

论文:https://arxiv.org/pdf/1910.09772v2.pdf

代码:https://github.com/google-research/google-research/tree/master/weak_disentangle

2. star:9819|Measuring Compositional Generalization: A Comprehensive Method on Realistic Data(测量成分泛化)

论文:https://arxiv.org/pdf/1912.09713v1.pdf

代码:https://github.com/google-research/google-research/tree/master/cfq

3. star:9819|Meta-Learning without Memorization(元学习)

论文:https://arxiv.org/pdf/1912.03820v3.pdf

代码:https://github.com/google-research/google-research/tree/master/meta_learning_without_memorization

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)

论文:https://arxiv.org/pdf/1907.10830v4.pdf

代码:https://github.com/taki0112/UGATIT

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-2ccnVZ00-1588414065101)(https://imgkr.cn-bj.ufileos.com/e9badd64-a632-4727-b345-ee67a92aa330.png)]

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

论文:https://arxiv.org/pdf/1908.03265v3.pdf

代码:https://github.com/LiyuanLucasLiu/RAdam

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-X6kbNpDA-1588414065103)(https://imgkr.cn-bj.ufileos.com/eb1b4aff-ffa7-4b3f-8836-44fff98f4cc5.png)]

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

论文:https://arxiv.org/pdf/1910.00935v3.pdf

代码:https://github.com/yuanming-hu/difftaichi

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

论文:https://arxiv.org/pdf/1911.06679v2.pdf

代码:https://github.com/tensorflow/federated/tree/master/tensorflow_federated/python/research/gans
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-ROmyEKkY-1588414065105)(https://imgkr.cn-bj.ufileos.com/2f5d8bca-4ee1-4ee1-94fe-7c8e26928260.png)]

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

论文:https://arxiv.org/pdf/1908.03568v3.pdf

代码:https://github.com/deepmind/bsuite
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-o0P9gbkH-1588414065106)(https://imgkr.cn-bj.ufileos.com/27f96404-6600-49f1-ab22-173df8192786.png)]

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

论文:https://arxiv.org/pdf/1910.10699v2.pdf

代码:https://github.com/HobbitLong/RepDistiller
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-7VqCAej8-1588414065108)(https://imgkr.cn-bj.ufileos.com/c305f16c-bb86-40bf-92d6-e260c8b73240.png)]

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

论文:https://arxiv.org/pdf/1911.03584v2.pdf

代码:https://github.com/epfml/attention-cnn

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

论文:https://arxiv.org/pdf/1912.02781v2.pdf

代码:https://github.com/rwightman/pytorch-image-models

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-piztaS5s-1588414065110)(https://imgkr.cn-bj.ufileos.com/9605092a-2b83-467a-bf3f-55009859f916.png)]

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

论文:https://arxiv.org/pdf/2001.00326v2.pdf

代码:https://github.com/D-X-Y/NAS-Projects

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

论文:https://openreview.net/pdf?id=HylxE1HKwS

代码:https://github.com/mit-han-lab/once-for-all

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

论文:https://arxiv.org/pdf/2002.06715v2.pdf

代码:https://github.com/google/edward2

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

论文:https://arxiv.org/pdf/1912.10917v2.pdf

代码:https://github.com/TAMU-VITA/FasterSeg
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-8eK0jphQ-1588414065111)(https://imgkr.cn-bj.ufileos.com/9e457112-c64b-4433-8ffb-c4a9be9f949f.png)]

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

论文:https://arxiv.org/pdf/1911.12247v2.pdf

代码:https://github.com/tkipf/c-swm
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-RQSCAjMf-1588414065112)(https://imgkr.cn-bj.ufileos.com/5bbd74a6-5cff-4f7c-9f82-7bd94d457251.png)]

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

论文:https://arxiv.org/pdf/2002.05512v1.pdf

代码:https://github.com/kam1107/RealnessGAN

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

论文:https://arxiv.org/pdf/1906.06310v3.pdf

代码:https://github.com/mileyan/Pseudo_Lidar_V2

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

论文:https://arxiv.org/pdf/2004.05155v1.pdf

代码:https://github.com/devendrachaplot/Neural-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)

论文:https://arxiv.org/pdf/2001.01526v2.pdf

代码:https://github.com/yxgeee/MMT

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

论文:https://arxiv.org/pdf/1912.09640v2.pdf

代码:https://github.com/meijieru/AtomNAS

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

论文:https://arxiv.org/pdf/1905.12265v3.pdf

代码:https://github.com/snap-stanford/pretrain-gnns/

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

论文:https://arxiv.org/pdf/2001.06838v2.pdf

代码:https://github.com/megvii-model/MABN

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

论文:https://arxiv.org/pdf/1907.10903v4.pdf

代码:https://github.com/DropEdge/DropEdge

25. star:107|Neural Arithmetic Units

论文:https://arxiv.org/pdf/2001.05016v1.pdf

代码:https://github.com/AndreasMadsen/stable-nalu

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

论文:https://arxiv.org/pdf/2002.12319v1.pdf

代码:https://github.com/TRI-ML/packnet-sfm

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-WwzAQgCI-1588414065114)(https://imgkr.cn-bj.ufileos.com/5565529f-381e-49a0-8356-fe570f1d5917.png)]

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

论文:https://arxiv.org/pdf/1911.03082v2.pdf

代码:https://github.com/malllabiisc/CompGCN

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

论文:https://arxiv.org/pdf/1910.02940v2.pdf

代码:https://github.com/hangg7/deformable-kernels/

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-48MKW1L3-1588414065115)(https://imgkr.cn-bj.ufileos.com/38a4640c-6032-4819-8006-d740308500e8.png)]

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

论文:https://arxiv.org/pdf/1912.12522v3.pdf

代码:https://github.com/antoyang/NAS-Benchmark

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

论文:https://arxiv.org/pdf/1909.09656v2.pdf

代码:https://github.com/automl/RobustDARTS

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)

论文:https://arxiv.org/pdf/2001.02525v2.pdf

代码:https://github.com/JaminFong/FNA

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

论文:https://arxiv.org/pdf/2002.04764v2.pdf

代码:https://github.com/apple/ml-capsules-inverted-attention-routing

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

论文:https://arxiv.org/pdf/1906.02694v2.pdf

代码:https://arxiv.org/pdf/1906.02694v2.pdf

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-3FBUmqBe-1588414065116)(https://imgkr.cn-bj.ufileos.com/cfc3fbf2-8034-45bc-acfb-ab2b56b94f8d.png)]

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

论文:https://arxiv.org/pdf/1905.11926v4.pdf

代码:https://github.com/deconvolutionpaper/deconvolution

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

论文:https://arxiv.org/pdf/2002.06470v1.pdf

代码:https://github.com/bayesgroup/pytorch-ensembles

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

论文:https://arxiv.org/pdf/2001.00689v2.pdf

代码:https://github.com/soochan-lee/CN-DPM

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

论文:https://openreview.net/pdf?id=Hkg-xgrYvH

代码:https://github.com/hushell/sib_meta_learn

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

论文:https://arxiv.org/pdf/2002.05969v2.pdf

代码:https://github.com/hyren/query2box

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

论文:https://openreview.net/pdf?id=BkgrBgSYDS

代码:https://github.com/HazyResearch/learning-circuits

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

论文:https://openreview.net/pdf?id=rJl31TNYPr

代码:https://github.com/anonymousjack/hijacking

打包下载戳这里

原创文章 44 获赞 83 访问量 11万+

猜你喜欢

转载自blog.csdn.net/Extremevision/article/details/105893481