328 citations · 706 across the 19 of their papers we have counts for
3 papers · 1 filter
Understanding Short-Range Memory Effects in Deep Neural Networks
Chengli Tan, Jiangshe Zhang, Junmin Liu
Stochastic gradient descent (SGD) is of fundamental importance in deep learning. Despite its simplicity, elucidating its efficacy remains challenging. Conventionally, the success o…
Toward a Controllable Disentanglement Network
Zengjie Song, Oluwasanmi Koyejo, Jiangshe Zhang
This paper addresses two crucial problems of learning disentangled image representations, namely controlling the degree of disentanglement during image editing, and balancing the d…
Learning Controllable Disentangled Representations with Decorrelation Regularization
Zengjie Song, Oluwasanmi Koyejo, Jiangshe Zhang
A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In thi…