In this paper, we propose a novel training strategy called SupFusion, wh...
This work explores the use of 3D generative models to synthesize trainin...
We present a simple but powerful architecture of convolutional neural
ne...
Modern activation layers use non-linear functions to activate the neuron...
We present a conceptually simple but effective funnel activation for ima...
We present a conceptually simple, flexible and effective framework for w...
Currently, the neural network architecture design is mostly guided by th...