Deep learning has recently achieved great success in many visual recognition tasks.
However, the deep neural networks (DNNs) are often perceived as black-boxes, making …

Diffusion models are powerful, but they require a lot of time and data to train. We propose
Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training …

The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

Deep neural networks have been applied in many applications exhibiting extraordinary
abilities in the field of computer vision. However, complex network architectures challenge …

Domain-specific hardware is becoming a promising topic in the backdrop of improvement
slow down for general-purpose processors due to the foreseeable end of Moore's Law …

Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of
neural networks. There has been a flurry of algorithms that try to solve this practical problem …

We introduce DeepInversion, a new method for synthesizing images from the image
distribution used to train a deep neural network. We" invert" a trained network (teacher) to …

Structural pruning of neural network parameters reduces computational, energy, and
memory transfer costs during inference. We propose a novel method that estimates the …