本帖最后由 上岸算法 于 2021-3-30 23:41 编辑 . }0 k3 L" L$ |
! }: B# \0 Y h! V" C% X& [作者简介：
7 C% N% e6 Z9 \. { n9 A小春老师是上岸算法的Machine Learning和Deep Learning导师，美国常春藤CS毕业，拥有多家FLAG任职经验，现任Machine Learning Scientist，在Deep Learning/Machine Learning/ NLP等领域有多篇paper发表和丰富的业界经验。担任面试官多年，曾帮助多位应届生设计辅导项目，修改简历，模拟面试直至斩获大厂Offer。6 [; `2 {* T4 t' b5 N; z
$ c! L# c1 d& r. }" l) A
计算机视觉是AI领域绝对的领头羊，从各大会议开始涌现Deep Learning的论文开始, 到今天应用到行业各个领域百花齐放, Deep Learning绝大多数里程碑式的进展都是从计算机视觉得到突破,并且应用到其他领域的。其原因之一是计算机视觉的信号相对于自然语言等其他信号更加直观, 更加易于被Embed成机器可以识别的模式。计算机视觉是各大公司招聘Research Scientist, Applied Scientist以及Machine Learning Engineer的一个非常重要的方面, 也是我们正在筹备开放的AI课程的必讲及详讲内容。 3 H3 E0 P; \6 y( F8 ^
今天小春老师带大家熟悉一下计算机视觉里程碑式的进展的经典论文。
. R1 ?- }8 [- D A2 {第一篇: LeCun, Yann, and Yoshua Bengio. "Convolutional networks for images, speech, and time series." The handbook of brain theory and neural networks 3361.10 (1995): 1995. 提出了CNN毫无疑问计算机视觉在Deep Learning领域的一大milestone % N5 @/ G1 v$ p
第二篇:Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012. 提出了AlexNet, 也是绝对的CV@Deep Learning的Breakthrough 4 ?! G" a0 R. D8 U" q
第三篇:Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). 提出了VGGNet使得Neural Networks 变得deep
7 ^* e# E% D( p# I: C; |. G/ B6 L" u
第四篇:Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. GoogLeNet使得Neural Networks 变得very deep
+ ?" P( Z7 l" @/ q0 y
第五篇: He, Kaiming, et al. "Deep residual learning for image recognition." arXiv preprint arXiv:1512.03385 (2015). 当年CVPR best paper, 进一步让Neural Networks 变得更加deep, 现在仍然是各大tech公司答CV系列的万金油 6 |& ~: A, \7 \$ U1 G% i: O
第六篇: Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014. 提出了GAN,现在仍然是各大fake狂们膜拜的神作 第七篇: Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." arXiv preprint arXiv:1312.6114 (2013). 提出了VAE, 是Unsupervised Deep Learning领域非常重要的一篇paper
, u, K% J( s3 I% X; X5 k8 x; m: }9 t. t
第八篇:Koch, Gregory, Richard Zemel, and Ruslan Salakhutdinov. "Siamese Neural Networks for One-shot Image Recognition."(2015) 提出了Siamese Neural Networks, 使得在很少量data的情况下,训练一个成功的NeuraNet成为可能 - z7 c4 l9 g, z1 ^
上岸4月份大厂面经公开课
9 E' a9 y$ Y4 K8 A" o3 \+ R8 W; D5 @3 i
- 04/05 -小K老师：简历项目深挖+BQ模拟面试
- 04/07 -米线儿老师：大数据在企业的应用以及工具
- 04/17 -莎莎老师： 出道即巅峰：转专业上岸亚麻Applied Scientist史
- 04/19 -小春老师： 推荐系统公开课
- 04/26 -小雨老师 ：SQL 带刷
- 04/28 -Ginger老师： 疫情下我是如何拿到Facebook DS Offer的？8 U: X" x9 K; W
【6节课免费参与】 ! m! B2 q- b( p( Q6 a( U
【DS 方向】
6 p& F( O) p' j# ?& P【SDE 方向】 , c4 w% ~! u q
下面的paper则是针对计算机视觉领域不同分支的,就不多介绍了,直接放paper: + k7 P8 g3 s# }. n
Object Detection [1] Szegedy, Christian, Alexander Toshev, and Dumitru Erhan. "Deep neural networks for object detection." Advances in Neural Information Processing Systems. 2013 [2] Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. (RCNN) [3] He, Kaiming, et al. "Spatial pyramid pooling in deep convolutional networks for visual recognition." European Conference on Computer Vision. Springer International Publishing, 2014 [4] Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE International Conference on Computer Vision. 2015. [5] Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object detection with region proposal networks." Advances in neural information processing systems. 2015 [6] Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." arXiv preprint arXiv:1506.02640 (2015). (YOLO,Oustanding Work, really practical) [7] Liu, Wei, et al. "SSD: Single Shot MultiBox Detector." arXiv preprint arXiv:1512.02325 (2015) [8] Dai, Jifeng, et al. "R-FCN: Object Detection via Region-based Fully Convolutional Networks." arXiv preprint arXiv:1605.06409 (2016) [9] He, Gkioxari, et al. "Mask R-CNN" arXiv preprint arXiv:1703.06870 (2017) [10] Bochkovskiy, Alexey, et al. "YOLOv4: Optimal Speed and Accuracy of Object Detection." arXiv preprint arXiv:2004.10934 (2020). [11] Tan, Mingxing, et al. “EfficientDet: Scalable and Efficient Object Detection." arXiv preprint arXiv:1911.09070 (2019). 2 s. q* N9 V- f8 x4 M% X% ~- m
Object Segmentation [1] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation.” in CVPR, 2015. [2] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. "Semantic image segmentation with deep convolutional nets and fully connected crfs." In ICLR, 2015. [3] Pinheiro, P.O., Collobert, R., Dollar, P. "Learning to segment object candidates." In: NIPS. 2015. [4] Dai, J., He, K., Sun, J. "Instance-aware semantic segmentation via multi-task network cascades." in CVPR. 2016 [5] Dai, J., He, K., Sun, J. "Instance-sensitive Fully Convolutional Networks." arXiv preprint arXiv:1603.08678 (2016)
' [4 s* h" C7 \2 Y! K/ T) p& l/ l
! o) o, w5 g/ j" m' i! r1 B: l/ E& X3 R, G' Q, b/ u! C$ h: k
) K+ \- C0 X( A3 F, ]. v
5 t9 f* k- ~: R2 F
" P8 o$ l2 f* ]8 Z3 U8 z- c5 {, L | 