Deep Growing Learning

By Guangcong Wang, Xiaohua Xie, J. Lai, Jiaxuan Zhuo. 2017

34 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Optimization & Training

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. Eugene Belilovsky
2. Michael Eickenberg
3. Simone Scardapane
4. Edouard Oyallon
5. Aurelio Uncini
6. Michele Scarpiniti
7. Enzo Baccarelli
8. Artsiom Sanakoyeu

In Computer Vision and Pattern Recognition

1. Eugene Belilovsky
2. Michael Eickenberg
3. Michele Scarpiniti
4. Enzo Baccarelli
5. Simone Scardapane
6. Aurelio Uncini
7. Edouard Oyallon
8. Artsiom Sanakoyeu

In Optimization & Training

1. Eugene Belilovsky
2. Simone Scardapane
3. Aurelio Uncini
4. Michele Scarpiniti
5. Enzo Baccarelli
6. Michael Eickenberg
7. Edouard Oyallon
8. Artsiom Sanakoyeu

Citations in the corpus

• AutoGrow: Automatic Layer Growing in Deep Convolutional Networks (2019, neutral): “eton architecture is known. AutoGrow performs in a scenario where the DNN depth is unknown hence we need to seek for the optimal depth. A growing sub-network was utilized for semi-supervised learning [34], and the new network fully converged before a next growth; AutoGrow targets on supervised learn”
• Why Should We Add Early Exits to Neural Networks? (2020, background): “[29]. When discussing overfitting and model selection, these are generally considered properties of a given network applied to a full dataset. However, recently, a large number of contributions, e.g., [38,73,48,7,3], have shown that, even in very complex datasets such as ImageNet, the majority of pat”
• Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks (2019, methodology): “initially provided labeled examples. However existing self-training approaches [12,52,32,31] are based on hand-crafted features which are much more limited than the features learned by CNNs. [27] and [45] use CNNs in the self-training framework, but they apply it to relatively simple classification d”
• Shallow Learning For Deep Networks (2018, unknown): “Mosca & Magoulas (2017); Wang et al. (2017) propose methods that stack progressively layers at each turn performing, end-to-end learning on the resulting network.”
• Greedy Layerwise Learning Can Scale to ImageNet (2018, background): “Mosca & Magoulas (2017); Wang et al. (2017) propose methods that progressively stack layers, performing end-to-end learning on the resulting network at each step.”