【综述专栏】各细分学习领域调研(A Survey for Learning Fields)
在科学研究中,从方法论上来讲,都应“先见森林,再见树木”。当前,人工智能学术研究方兴未艾,技术迅猛发展,可谓万木争荣,日新月异。对于AI从业者来说,在广袤的知识森林中,系统梳理脉络,才能更好地把握趋势。为此,我们精选国内外优秀的综述文章,开辟“综述专栏”,敬请关注。
地址:https://www.zhihu.com/people/zhou-peng-fei-98
Fine-Grained Learning Contrast Learning Causal Learning Metric Learning Auto Learning
01
02
03
04
05
06
[1] Tang Y , Wang J , Wang X , et al. Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence (TPAMI), 2018, PP(99):1-1.
[2] Zhong, Yuanyi, et al. “Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer.” ECCV, 2020.
[3] Dong-Dong Chen ,Wei Wang ,Wei Gao and Zhi-Hua Zhou. “Tri-Net for Semi-Supervised Deep Learning.” IJCAI'18 Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018, pp. 2014–2020.
[4] Dosovitskiy, Alexey, et al. “An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale.” ArXiv, 2020.
[5] He, Kaiming, et al. “Momentum Contrast for Unsupervised Visual Representation Learning.” CVPR, 2020, pp. 9729–9738.
[6] Chen, Ting & Kornblith, Simon & Hinton, Geoffrey. A Simple Framework for Contrastive Learning of Visual Representations. ICML, 2020
[7] Chen, Xinlei, and Kaiming He. "Exploring Simple Siamese Representation Learning." ArXiv, 2020.
[8] Li, Yandong, et al. “Improving Object Detection with Selective Self-Supervised Self-Training.” ECCV (29), 2020, pp. 589–607.
[9]Shu, Jun, et al. “Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting.” NeurIPS, vol. 32, 2019, pp. 1919–1930.
[10]Qiao, Siyuan, et al. “Few-Shot Image Recognition by Predicting Parameters from Activations.” CVPR, 2018, pp. 7229–7238.
[11]Zhu, Yaohui, Chenlong Liu, and Shuqiang Jiang. "Multi-attention meta learning for few-shot fine-grained image recognition." IJCAI, 2020.
[12]Wei, Xiu-Shen, et al. “RPC: A Large-Scale Retail Product Checkout Dataset.” ArXiv Preprint ArXiv:1901.07249, 2019.
[13]Belouadah, Eden, and Adrian Popescu. "Il2m: Class incremental learning with dual memory." CVPR, 2019.
[14]MLARajasegaran, Jathushan, et al. "Random path selection for incremental learning." NeurIPS, 2019.
[15]Perez-Rua, Juan-Manuel, et al. "Incremental few-shot object detection." CVPR, 2020.
[16]Cermelli, Fabio, et al. "Modeling the background for incremental learning in semantic segmentation." CVPR, 2020.
[17]Ghiasi, Golnaz & Cui, Yin & Srinivas, Aravind & Qian, Rui & Lin, Tsung-Yi & Cubuk, Ekin & Le, Quoc & Zoph, Barret. Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation, 2020.
“综述专栏”历史文章
Distributed Training:强化学习并行训练论文合集
用放大镜看Transformer——总体和各个模块的结构到底是什么样的
注意力机制到底是什么——基于常识的基本结构介绍
乘风破浪的PTM:两年来预训练模型的技术进展
对比学习(Contrastive Learning)综述
深度学习中的Normalization模型
目标检测之Neck选择
基于能量的模型
Image matting—图像抠图入门篇
深度生成式模型
知识蒸馏在推荐系统的应用
深度学习中眼花缭乱的Normalization学习总结
关于知识图谱和语言模型的想法
循环神经网络RNN(含LSTM,GRU)小综述
一文讲述LSTM及其变体
更多综述专栏文章,
请点击文章底部“阅读原文”查看
分享、点赞、在看,给个三连击呗!