編譯：ronghuaiyang

導讀

2020年Papers with Code 中最頂流的論文，程式碼和benchmark。

Papers with Code 中收集了各種機器學習的內容：論文，程式碼，結果，方便發現和比較。透過這些資料，我們可以瞭解ML社群中，今年哪些東西最有意思。下面我們總結了2020年最熱門的帶程式碼的論文、程式碼庫和benchmark。

2020頂流論文

Tan等人的EfficientDet是2020年在Papers with Code上被訪問最多的論文。

EfficientDet: Scalable and Efficient Object Detection — Tan et al https://paperswithcode.com/paper/efficientdet-scalable-and-efficient-objectFixing the train-test resolution discrepancy — Touvron et al https://paperswithcode.com/paper/fixing-the-train-test-resolution-discrepancy-2ResNeSt: Split-Attention Networks — Zhang et al https://paperswithcode.com/paper/resnest-split-attention-networksBig Transfer (BiT) — Kolesnikov et al https://paperswithcode.com/paper/large-scale-learning-of-general-visualObject-Contextual Representations for Semantic Segmentation — Yuan et al https://paperswithcode.com/paper/object-contextual-representations-forSelf-training with Noisy Student improves ImageNet classification — Xie et al https://paperswithcode.com/paper/self-training-with-noisy-student-improvesYOLOv4: Optimal Speed and Accuracy of Object Detection — Bochkovskiy et al https://paperswithcode.com/paper/yolov4-optimal-speed-and-accuracy-of-objectAn 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-1Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer — Raffel et al https://paperswithcode.com/paper/exploring-the-limits-of-transfer-learningHierarchical Multi-Scale Attention for Semantic Segmentation — Tao et al https://paperswithcode.com/paper/hierarchical-multi-scale-attention-for2020頂流程式碼庫

Transformers是2020年在Papers with Code上被訪問最多的程式碼庫

Transformers — Hugging Face — https://github.com/huggingface/transformersPyTorch Image Models — Ross Wightman — https://github.com/rwightman/pytorch-image-modelsDetectron2 — FAIR — https://github.com/facebookresearch/detectron2InsightFace — DeepInsight — https://github.com/deepinsight/insightfaceImgclsmob — osmr — https://github.com/osmr/imgclsmobDarkNet — pjreddie — https://github.com/pjreddie/darknetPyTorchGAN — Erik Linder-Norén — https://github.com/eriklindernoren/PyTorch-GANMMDetection — OpenMMLab — https://github.com/open-mmlab/mmdetectionFairSeq — PyTorch — https://github.com/pytorch/fairseqGluon CV — DMLC — https://github.com/dmlc/gluon-cv2020頂流Benchmarks

ImageNet是2020年在Papers with Code上訪問最多的benchmark

ImageNet — Image Classification — https://paperswithcode.com/sota/image-classification-on-imagenetCOCO — Object Detection / Instance Segmentation — https://paperswithcode.com/sota/object-detection-on-cocoCityscapes — Semantic Segmentation — https://paperswithcode.com/sota/semantic-segmentation-on-cityscapesCIFAR-10 — Image Classification — https://paperswithcode.com/sota/image-classification-on-cifar-10CIFAR-100 — Image Classification — https://paperswithcode.com/sota/image-classification-on-cifar-100PASCAL VOC 2012 — Semantic Segmentation — https://paperswithcode.com/sota/semantic-segmentation-on-pascal-voc-2012MPII Human Pose — Pose Estimation — https://paperswithcode.com/sota/pose-estimation-on-mpii-human-poseMarket-1501 — Person Re-Identification — https://paperswithcode.com/sota/person-re-identification-on-market-1501MNIST — Image Classification — https://paperswithcode.com/sota/image-classification-on-mnistHuman 3.6M — Human Pose Estimation -https://paperswithcode.com/sota/pose-estimation-on-mpii-human-pose

英文原文：https://medium.com/paperswithcode/papers-with-code-2020-review-938146ab9658