顶级AI资源 | 2020年最热的AI论文、代码和基准数据集「年终盘点」「AI优质资源」...

关注：耕智能，深耕AI脱水干货

作者：Ross Taylor  编译：ronghuaiyang  来源：AI公园

转载请联系作者

2020年Papers with Code 中最顶流的论文，代码和benchmark。

Papers with Code 中收集了各种机器学习的内容：论文，代码，结果，方便发现和比较。通过这些数据，我们可以了解ML社区中，今年哪些东西最有意思。下面我们总结了2020年最热门的带代码的论文、代码库和benchmark。

2020顶流论文

Tan等人的EfficientDet是2020年在Papers with Code上被访问最多的论文。

1. EfficientDet: Scalable and Efficient Object Detection — Tan et al https://paperswithcode.com/paper/efficientdet-scalable-and-efficient-object

2. Fixing the train-test resolution discrepancy — Touvron et al https://paperswithcode.com/paper/fixing-the-train-test-resolution-discrepancy-2

3. ResNeSt: Split-Attention Networks — Zhang et al https://paperswithcode.com/paper/resnest-split-attention-networks

4. Big Transfer (BiT) — Kolesnikov et al https://paperswithcode.com/paper/large-scale-learning-of-general-visual

5. Object-Contextual Representations for Semantic Segmentation — Yuan et al https://paperswithcode.com/paper/object-contextual-representations-for

6. Self-training with Noisy Student improves ImageNet classification — Xie et al https://paperswithcode.com/paper/self-training-with-noisy-student-improves

7. YOLOv4: Optimal Speed and Accuracy of Object Detection — Bochkovskiy et al https://paperswithcode.com/paper/yolov4-optimal-speed-and-accuracy-of-object

8. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale — Dosovitskiy et al https://paperswithcode.com/paper/an-image-is-worth-16x16-words-transformers-1

9. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer — Raffel et al https://paperswithcode.com/paper/exploring-the-limits-of-transfer-learning

10. Hierarchical Multi-Scale Attention for Semantic Segmentation — Tao et al https://paperswithcode.com/paper/hierarchical-multi-scale-attention-for

2020顶流代码库

Transformers是2020年在Papers with Code上被访问最多的代码库

1. Transformers — Hugging Face — https://github.com/huggingface/transformers

2. PyTorch Image Models — Ross Wightman — https://github.com/rwightman/pytorch-image-models

3. Detectron2 — FAIR — https://github.com/facebookresearch/detectron2

4. InsightFace — DeepInsight — https://github.com/deepinsight/insightface

5. Imgclsmob — osmr — https://github.com/osmr/imgclsmob

6. DarkNet — pjreddie — https://github.com/pjreddie/darknet

7. PyTorchGAN — Erik Linder-Norén — https://github.com/eriklindernoren/PyTorch-GAN

8. MMDetection — OpenMMLab — https://github.com/open-mmlab/mmdetection

9. FairSeq — PyTorch — https://github.com/pytorch/fairseq

10. Gluon CV — DMLC — https://github.com/dmlc/gluon-cv

2020顶流Benchmarks

ImageNet是2020年在Papers with Code上访问最多的benchmark

1. ImageNet — Image Classification — https://paperswithcode.com/sota/image-classification-on-imagenet

2. COCO — Object Detection / Instance Segmentation — https://paperswithcode.com/sota/object-detection-on-coco

3. Cityscapes — Semantic Segmentation — https://paperswithcode.com/sota/semantic-segmentation-on-cityscapes

4. CIFAR-10 — Image Classification — https://paperswithcode.com/sota/image-classification-on-cifar-10

5. CIFAR-100 — Image Classification — https://paperswithcode.com/sota/image-classification-on-cifar-100

6. PASCAL VOC 2012 — Semantic Segmentation — https://paperswithcode.com/sota/semantic-segmentation-on-pascal-voc-2012

7. MPII Human Pose — Pose Estimation — https://paperswithcode.com/sota/pose-estimation-on-mpii-human-pose

8. Market-1501 — Person Re-Identification — https://paperswithcode.com/sota/person-re-identification-on-market-1501

9. MNIST — Image Classification — https://paperswithcode.com/sota/image-classification-on-mnist

10. Human 3.6M — Human Pose Estimation -https://paperswithcode.com/sota/pose-estimation-on-mpii-human-pose

历史精华好文

• 专辑1：AI工程落地

• 专辑2：AI核心算法

• 专辑3：AI优质资源

交流合作

请加微信号：yan_kylin_phenix，注明姓名+单位+从业方向+地点，非诚勿扰。