咨询电话: 020-88888888
2021年不可错过的40篇AI论文,你都读过吗?!
发布于 2023-11-27 11:05 阅读()
来自机器之心
欢迎关注 @机器学习社区 ,专注学术论文、机器学习、人工智能、Python技巧
虽然世界仍在从新冠疫情的破坏中复苏,人们无法向从前那样时常线下相聚、共同探讨交流关于学术领域的最新问题,但AI研究也没有停下跃进的步伐。
转眼就是2021年底了,一年就这么就过去了,时光好像被偷走一样。细细数来,你今年读了多少论文?
一名加拿大博主Louis Bouchard以发布时间为顺序,整理出了近40篇2021年不可错过的优秀论文。整体来看,合集中的论文偏重计算机视觉方向。
建了深度学习交流群!想要交流群的同学,可以直接加微信号:mlc2060。加的时候备注一下:研究方向+学校/公司+知乎,即可。然后就可以拉你进群了。
以下是每篇论文的详细信息:
1、DALL·E: Zero-Shot Text-to-Image Generation from OpenAI
![](https://pic1.zhimg.com/v2-6644adcc941fb960a58813ce2f942150_b.jpg)
论文链接:https://arxiv.org/pdf/2102.12092.pdf
代码地址:https://github.com/openai/DALL-E
视频解读:https://youtu.be/DJToDLBPovg
2、VOGUE: Try-On by StyleGAN Interpolation Optimization
论文链接:https://vogue-try-on.github.io/static_files/resources/VOGUE-virtual-try-on.pdf
视频解读:https://youtu.be/i4MnLJGZbaM
3、Taming Transformers for High-Resolution Image Synthesis
![](https://pic1.zhimg.com/v2-876755845da21e31f90519003d13d7ac_b.jpg)
论文链接:https://compvis.github.io/taming-transformers/
代码地址:https://github.com/CompVis/taming-transformers
视频解读:https://youtu.be/JfUTd8fjtX8
4、Thinking Fast And Slow in AI
![](https://pic2.zhimg.com/v2-8bdea537b1db503deaf4953f307bb35d_b.jpg)
论文链接:https://arxiv.org/abs/2010.06002
视频解读:https://youtu.be/3nvAaVSQxs4
5、Automatic detection and quantification of floating marine macro-litter in aerial images
![](https://pic2.zhimg.com/v2-3cd9e64e8b68a51ffda0cabca0dbd3d1_b.jpg)
论文链接:https://doi.org/10.1016/j.envpol.2021.116490
代码地址:https://github.com/amonleong/MARLIT
视频解读:https://youtu.be/2dTSsdW0WYI
6、ShaRF: Shape-conditioned Radiance Fields from a Single View
![](https://pic2.zhimg.com/v2-5bf7b36e8ca26e6f6f9c51023e5a5cbd_b.jpg)
论文链接:https://arxiv.org/abs/2102.08860
代码地址:http://www.krematas.com/sharf/index.html
视频解读:https://youtu.be/gHkkrNMlGNg
7、Generative Adversarial Transformers
![](https://pic1.zhimg.com/v2-87ddf82daf5115f6b3d1d9501cd4d620_b.jpg)
论文链接:https://arxiv.org/pdf/2103.01209.pdf
代码地址:https://github.com/dorarad/gansformer
视频解读:https://youtu.be/HO-_t0UArd4
8、We Asked Artificial Intelligence to Create Dating Profiles. Would You Swipe Right?
论文链接:https://studyonline.unsw.edu.au/blog/ai-generated-dating-profile
代码地址:https://colab.research.google.com/drive/1VLG8e7YSEwypxU-noRNhsv5dW4NfTGce#forceEdit=true&sandboxMode=true&scrollTo=aeXshJM-Cuaf
视频解读:https://youtu.be/IoRH5u13P-4
9、Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
![](https://pic3.zhimg.com/v2-85f47b6271a688b81ca703105fdd050e_b.jpg)
论文链接:https://arxiv.org/abs/2103.14030v2
代码地址:https://github.com/microsoft/Swin-Transformer
视频解读:https://youtu.be/QcCJJOLCeJQ
10、IMAGE GANS MEET DIFFERENTIABLE RENDERING FOR INVERSE GRAPHICS AND INTERPRETABLE 3D NEURAL RENDERING
![](https://pic3.zhimg.com/v2-7fbeaabe4e51e5a088cb757248019006_b.jpg)
论文链接:https://arxiv.org/pdf/2010.09125.pdf
视频解读:https://youtu.be/dvjwRBZ3Hnw
11、Deep nets: What have they ever done for vision?
![](https://pic1.zhimg.com/v2-dbe982f9b28a1b542946480bd8606358_b.jpg)
论文链接:https://arxiv.org/abs/1805.04025
视频解读:https://youtu.be/GhPDNzAVNDk
12、Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
![](https://pic4.zhimg.com/v2-249eee30ac70002ade07cbfe4fc5838f_b.jpg)
论文链接:https://arxiv.org/pdf/2012.09855.pdf
代码地址:https://github.com/google-research/google-research/tree/master/infinite_nature
视频解读:https://youtu.be/NIOt1HLV_Mo
在线试用:https://colab.research.google.com/github/google-research/google-research/blob/master/infinite_nature/infinite_nature_demo.ipynb#scrollTo=sCuRX1liUEVM
13、Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control
![](https://pic3.zhimg.com/v2-ad0f540fb576233b228b12f94871637a_b.jpg)
论文链接:https://arxiv.org/abs/2103.13452
视频解读:https://youtu.be/wNBrCRzlbVw
14、Total Relighting: Learning to Relight Portraits for Background Replacement
![](https://pic3.zhimg.com/v2-96df0ff4b1328068dd845cd35f38a5f6_b.jpg)
论文链接:https://augmentedperception.github.io/total_relighting/total_relighting_paper.pdf
视频解读:https://youtu.be/rVP2tcF_yRI
15、LASR: Learning Articulated Shape Reconstruction from a Monocular Video
![](https://pic3.zhimg.com/v2-320c3204d771e0517ca49cf6bc25a4c6_b.jpg)
论文链接:https://openaccess.thecvf.com/content/CVPR2021/papers/Yang_LASR_Learning_Articulated_Shape_Reconstruction_From_a_Monocular_Video_CVPR_2021_paper.pdf
代码地址:https://github.com/google/lasr
视频解读:https://youtu.be/lac7wqjS-8E
16、Enhancing Photorealism Enhancement
![](https://pic2.zhimg.com/v2-38c274c994158af0fb972c192f0acea1_b.jpg)
论文链接:http://vladlen.info/papers/EPE.pdf
代码地址:https://github.com/isl-org/PhotorealismEnhancement
视频解读:https://youtu.be/3rYosbwXm1w
17、DefakeHop: A Light-Weight High-Performance Deepfake Detector
![](https://pic1.zhimg.com/v2-585ebabe0dd3b052206e6b26ec4eee64_b.jpg)
论文链接:https://arxiv.org/abs/2103.06929
视频解读:https://youtu.be/YMir8sRWRos
18、High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
![](https://pic1.zhimg.com/v2-f54fd0f0b06ef23ab5ece702203a50a4_b.jpg)
论文链接:https://arxiv.org/pdf/2105.09188.pdf
代码地址:https://github.com/csjliang/LPTN
视频解读:https://youtu.be/X7WzlAyUGPo
19、Barbershop: GAN-based Image Compositing using Segmentation Masks
![](https://pic3.zhimg.com/v2-b9bd3574a129881499f1d75d555a5706_b.jpg)
论文链接:https://arxiv.org/pdf/2106.01505.pdf
代码地址:https://github.com/ZPdesu/Barbershop
视频解读:https://youtu.be/HtqYMvBVJD8
20、TextStyleBrush: Transfer of text aesthetics from a single example
![](https://pic3.zhimg.com/v2-59e5ae207dda73548b54b78f499d5fbe_b.jpg)
论文链接:https://arxiv.org/abs/2106.08385
代码地址:https://github.com/facebookresearch/IMGUR5K-Handwriting-Dataset?fbclid=IwAR0pRAxhf8Vg-5H3fA0BEaRrMeD21HfoCJ-so8V0qmWK7Ub21dvy_jqgiVo
视频解读:https://youtu.be/hhAri5fl-XI
21、Animating Pictures with Eulerian Motion Fields
![](https://pic2.zhimg.com/v2-036a2b6ff836012647fdba2633152be9_b.jpg)
论文链接:https://arxiv.org/abs/2011.15128
代码地址:https://eulerian.cs.washington.edu/
视频解读:https://youtu.be/KgTa2r7d0I0
22、CVPR 2021 Best Paper Award: GIRAFFE - Controllable Image Generation
![](https://pic2.zhimg.com/v2-ad3b9a3f677886d0e588de814801d091_b.jpg)
论文链接:http://www.cvlibs.net/publications/Niemeyer2021CVPR.pdf
代码地址:https://github.com/autonomousvision/giraffe
视频解读:https://youtu.be/JIJkURAkCxM
23、GitHub Copilot & Codex: Evaluating Large Language Models Trained on Code
![](https://pic3.zhimg.com/v2-3d95f085a7e64f5c75a60a66bf0a6f4a_b.jpg)
论文链接:https://arxiv.org/pdf/2107.03374.pdf
代码地址:https://copilot.github.com/
视频解读:https://youtu.be/az3oVVkTFB8
24、Apple: Recognizing People in Photos Through Private On-Device Machine Learning
![](https://pic4.zhimg.com/v2-cbc4d58d44bbe1f3cf727ecdd535b00b_b.jpg)
论文链接:https://machinelearning.apple.com/research/recognizing-people-photos
视频解读:https://youtu.be/LIV-M-gFRFA
25、Image Synthesis and Editing with Stochastic Differential Equations
![](https://pic3.zhimg.com/v2-4e26a5cd73caedc1791f444269687a56_b.jpg)
论文链接:https://arxiv.org/pdf/2108.01073.pdf
代码地址:https://github.com/ermongroup/SDEdit
视频解读:https://youtu.be/xoEkSWJSm1k
https://colab.research.google.com/drive/1KkLS53PndXKQpPlS1iK-k1nRQYmlb4aO?usp=sharing
26、Sketch Your Own GAN
![](https://pic4.zhimg.com/v2-55d1a13883dc40ca06867c7dd2161a53_b.jpg)
论文链接:https://arxiv.org/abs/2108.02774
代码地址:https://github.com/PeterWang512/GANSketching
视频解读:https://youtu.be/vz_wEQkTLk0
27、Tesla's Autopilot Explained在今年8月的特斯拉AI日上,特斯拉AI总监Andrej Karpathy和其他人展示了特斯拉是如何通过八个摄像头采集图像,打造了基于视觉的自动驾驶系统。
![](https://pic3.zhimg.com/v2-1fb6e48f5de7d256c119bb64946e7f12_b.jpg)
视频解读:https://youtu.be/DTHqgDqkIRw
28、Styleclip: Text-driven manipulation of StyleGAN imagery
![](https://pic1.zhimg.com/v2-765efc73daab69d4e693733a27e306c8_b.jpg)
论文链接:https://arxiv.org/abs/2103.17249
代码地址:https://github.com/orpatashnik/StyleCLIP
视频解读:https://youtu.be/RAXrwPskNso
https://colab.research.google.com/github/orpatashnik/StyleCLIP/blob/main/notebooks/StyleCLIP_global.ipynb
29、TimeLens: Event-based Video Frame Interpolation
![](https://pic2.zhimg.com/v2-45a2ba2c49d10f4d62b72cfeab45c611_b.jpg)
论文链接:http://rpg.ifi.uzh.ch/docs/CVPR21_Gehrig.pdf
代码地址:https://github.com/uzh-rpg/rpg_timelens
视频解读:https://youtu.be/HWA0yVXYRlk
30、Diverse Generation from a Single Video Made Possible
![](https://pic1.zhimg.com/v2-b064316a5ca919c58c5e12988fd72a60_b.jpg)
论文链接:https://arxiv.org/abs/2109.08591
代码地址:https://nivha.github.io/vgpnn/
视频解读:https://youtu.be/Uy8yKPEi1dg
31、Skillful Precipitation Nowcasting using Deep Generative Models of Radar
![](https://pic2.zhimg.com/v2-ec2047e2163c7e0cda681e1f135e249d_b.jpg)
论文链接:https://www.nature.com/articles/s41586-021-03854-z
代码地址:https://github.com/deepmind/deepmind-research/tree/master/nowcasting
视频解读:https://youtu.be/dlSIq64psEY
32、The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks
![](https://pic2.zhimg.com/v2-18f442ca370b97c7de0f70fb9ba5fbd5_b.jpg)
论文链接:https://arxiv.org/pdf/2110.09958.pdf
代码地址:https://cocktail-fork.github.io/
视频解读:https://youtu.be/Rpxufqt5r6I
33、ADOP: Approximate Differentiable One-Pixel Point Rendering
![](https://pic3.zhimg.com/v2-aaa21feef598113b438b596236ebc466_b.jpg)
论文链接:https://arxiv.org/pdf/2110.06635.pdf
代码地址:https://github.com/darglein/ADOP
视频解读:https://youtu.be/Jfph7Vld_Nw
34、(Style)CLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis
![](https://pic2.zhimg.com/v2-87d517abe3e15dc7ebe722a94dc441f1_b.jpg)
CLIPDraw论文链接:https://arxiv.org/abs/2106.14843
在线试用:https://colab.research.google.com/github/kvfrans/clipdraw/blob/main/clipdraw.ipynb
![](https://pic2.zhimg.com/v2-d4706b559b5e9ae3e4901f358693f6c1_b.jpg)
StyleCLIPDraw论文链接:https://arxiv.org/abs/2111.03133
在线试用:https://colab.research.google.com/github/pschaldenbrand/StyleCLIPDraw/blob/master/Style_ClipDraw.ipynb
视频解读:https://youtu.be/5xzcIzHm8Wo
35、SwinIR: Image restoration using swin transformer
![](https://pic1.zhimg.com/v2-631ffd56f4c2d0affa92a99803869668_b.jpg)
论文链接:https://arxiv.org/abs/2108.10257
代码地址:https://github.com/JingyunLiang/SwinIR
视频解读:https://youtu.be/GFm3RfrtDoU
https://replicate.ai/jingyunliang/swinir
36、EditGAN: High-Precision Semantic Image Editing
论文链接:https://arxiv.org/abs/2111.03186
代码地址:https://nv-tlabs.github.io/editGAN/
视频解读:https://youtu.be/bus4OGyMQec
37、CityNeRF: Building NeRF at City Scale
![](https://pic3.zhimg.com/v2-39cc0cde927decced83e2b0337413062_b.jpg)
论文链接:https://arxiv.org/pdf/2112.05504.pdf
代码地址:https://city-super.github.io/citynerf/
视频解读:https://youtu.be/swfx0bJMIlY
38、ClipCap: CLIP Prefix for Image Captioning
论文链接:https://arxiv.org/abs/2111.09734
代码地址:https://github.com/rmokady/CLIP_prefix_caption
视频解读:https://youtu.be/VQDrmuccWDo
在线试用:https://colab.research.google.com/drive/1tuoAC5F4sC7qid56Z0ap-stR3rwdk0ZV?usp=sharing
当然,博主在整理的过程中也不能保证完美。经网友提醒,这里可以手动添加一项突破性研究:「AlphaFold」。
![](https://pic3.zhimg.com/v2-3624ec12740b6667b86a35c44f9dc78e_b.jpg)
去年,谷歌旗下人工智能技术公司 DeepMind 宣布深度学习算法「Alphafold」破解了出现五十年之久的蛋白质分子折叠问题。2021年7月,AlphaFold 的论文正式发表在《Nature》杂志上。
![](https://pic1.zhimg.com/v2-e5cdbf57fe8bdab9840aa890cd142884_b.jpg)
论文链接:https://www.nature.com/articles/s41586-021-03819-2
这项研究被评为Nature年度技术突破,Alphafold 的缔造者之一 John Jumper 也被评为《Nature》2021 年度十大科学人物。DeepMind也已经将他们的预测结果免费开放给公众。
对于你来说,2021年最令人印象深刻的论文又是哪篇呢?
原文链接:https://www.louisbouchard.ai/2021-ai-papers-review/
即插即用 | 超越CBAM,全新注意力机制,GAM不计成本提高精度(附Pytorch实现)
豪取4个SOTA,谷歌魔改Transformer登NeurIPS 2021!一层8个token比1024个还好用
精度超越Transformer,MIT、港大提出基于物理模型的Neuro-Symbolic视觉推理框架
清华南开发布attention 7年全回顾:注意力机制还有7大问题要研究!
GAN“家族”又添新成员——EditGAN,不但能自己修图,还修得比你我都好
大道至简,何恺明新论文火了:Masked Autoencoders让计算机视觉通向大模型
kaggle、TDS、arXiv......,我最喜欢的10个顶级数据科学资源
NLP 领域最权威的 CS224N 2021冬季课程全部上线,Manning主讲!
当Transformer又遇见U-Net!Transformer-Unet:医学图像分割新工作
新闻资讯
-
关于开展“清朗·优化营商网络环 07-01
-
电竞大神是女生 07-01
-
持续优化营商“软”环境, 培育 07-01
-
神经网络拓扑结构是什么,神经网 07-01
-
代充抖币,信息差项目,一个月搞 07-01
-
抖音极速版最新版下载_3 07-01
-
SEO工作原理及优化解析 07-01
-
关于进一步建立健全涉企服务工作 07-01