Semi-supervised Deep Learning with Memory

By Yanbei Chen, Xiatian Zhu, Shaogang Gong. 2018

70 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Quoc V. Le
2. Mohit Bansal
3. Minh-Thang Luong
4. Yejin Choi
5. Eduard H. Hovy
6. Zeynep Akata
7. Jianfeng Gao
8. Percy Liang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Yi Yang
4. Ming-Hsuan Yang
5. Quoc V. Le
6. Trevor Darrell
7. Alan L. Yuille
8. Xiaogang Wang

In Radiology, Nuclear Medicine and Imaging

1. Robby T. Tan
2. Lu Liu
3. Hao Yang
4. Hao Chen
5. Hao-Yu Wu
6. Xiatian Zhu
7. Quoc V. Le
8. Zeynep Akata

In Representation & Self-Supervised Learning

1. Quoc V. Le
2. Minh-Thang Luong
3. Qizhe Xie
4. Eduard H. Hovy
5. Robby T. Tan
6. Lu Liu
7. Hao-Yu Wu
8. Hao Yang

Citations in the corpus

• Self-Training With Noisy Student Improves ImageNet Classification (2019, background): “Apart from self-training, another important line of work in semi-supervised learning [11, 96] is based on consistency training [5, 60, 43, 79, 52, 48, 58, 12, 15, 56, 2, 45, 82, 84, 7, 91].”
• Certainty-Driven Consistency Loss for Semi-supervised Learning (2019, methodology): “∗ indicate equal contributions With the tremendous success of deep learning, recently proposed semi-supervised learning methods have achieved remarkable results [11, 12, 13, 14, 3, 15, 16, 17, 18].”
• Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, background): “…to impute the labels of samples classified with high confidence [67], it is later extended to train deep neural networks in SSL setting by minimizing the entropy of the class assignments either derived in the prediction space [25], [26], [37], [47], [68] or the feature space [69], as detailed next.”
• Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning (2019, methodology): “[31] measure the consistency between the current prediction and an additional prediction for the same sample given by an external memory module that keeps track of previous representations.”
• Decoupled Certainty-Driven Consistency Loss for Semi-supervised Learning (2019, background): “58) with the state-of-the-art method MA-DNN [6] (34.”
• Detecting 11K Classes: Large Scale Object Detection Without Fine-Grained Bounding Boxes (2019, methodology): “Unlike [4], our semi-supervised fine-grained detection task is a two-level semi-supervised problem.”