computer vision

Is Attention Better Than Matrix Decomposition?

As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery. However, is hand-crafted attention irreplaceable when modeling the global context? Our …

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

Our study aims to explicitly predict overlap relations and resolve overlaps in a differentiable way for the panoptic output.

Expectation Maximization Attention Networks for Semantic Segmentation

We formulate the attention mechanism into an expectation-maximization manner and iteratively estimate a much more compact set of bases upon which the attention maps are computed.

R^2 Net Recurrent and Recursive Network for Sparse View CT Artifacts Removal

We propose a novel neural network architecture to reduce streak artifacts generated in sparse-view 2D Cone Beam Computed To-mography (CBCT) image reconstruction.

Recurrent Squeeze-and-Excitation Net for Single Image Deraining

We propose a novel deep network architecture based on deep convolutional and recurrent neural networksfor single image deraining.

Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution

We propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the high resolution (HR) image with better textural details in the wavelet domain.

Robust Kernel Estimation with Outliers Handling for Image Deblurring

We present an algorithm to address this problem by exploiting reliable edges and removing outliers in the intermediate latent images, thereby estimating blur kernels robustly