253 citations · 745 across the 24 of their papers we have counts for
8 papers · 1 filter
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation
Liwei Wang, Lunjia Hu, Jiayuan Gu +4
It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory an…
Gradient Descent Finds Global Minima of Deep Neural Networks
Simon S. Du, Jason D. Lee, Haochuan Li +2
Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero tr…
Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
Aoxue Li, Zhiwu Lu, Jiechao Guan +3
Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to unseen ones so that the latter can be recognised without any training samples. This is made possible by lea…
Improving the Generalization of Adversarial Training with Domain Adaptation
Chuanbiao Song, Kun He, Liwei Wang +1
By injecting adversarial examples into training data, adversarial training is promising for improving the robustness of deep learning models. However, most existing adversarial tra…
Learning to Navigate for Fine-grained Classification
Ze Yang, Tiange Luo, Dong Wang +3
Fine-grained classification is challenging due to the difficulty of finding discriminative features. Finding those subtle traits that fully characterize the object is not straightf…
FRAGE: Frequency-Agnostic Word Representation
Chengyue Gong, Di He, Xu Tan +3
Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks. Although it is widely a…