no code implementations • 16 Jun 2021 • Lanlan Liu, Yuting Zhang, Jia Deng, Stefano Soatto
Recent work introduced progressive network growing as a promising way to ease the training for large GANs, but the model design and architecture-growing strategy still remain under-explored and needs manual design for different image data.
1 code implementation • ECCV 2020 • Lanlan Liu, Mingzhe Wang, Jia Deng
We introduce UniLoss, a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses.
1 code implementation • ICCV 2019 • Lanlan Liu, Michael Muelly, Jia Deng, Tomas Pfister, Li-Jia Li
This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense.
no code implementations • 2 Jan 2017 • Lanlan Liu, Jia Deng
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution.