Deep Learning
Top-KAST: Top-K Always Sparse Training
For very large models this requirement can be prohibitive.
Encoding Spatial Distribution of Convolutional Features for Texture Representation
This enables a CNN to encode the regularity on the spatial arrangement of image features, leading to a robust yet discriminative spectrum descriptor.
A Fast Post-Training Pruning Framework for Transformers
Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models.
Pluralistic Image Completion with Gaussian Mixture Models
Specifically, we introduce a unified probabilistic graph model that represents the complex interactions in image completion.
Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution
Single Image Super-Resolution (SISR) is a low-level visual task to recover High-Resolution (HR) images from its degraded Low-Resolution (LR) counterparts.
Structure-A ware Image Segmentation with Homotopy Warping
Besides per-pixel accuracy, topological correctness is also crucial for the segmentation of images with fine-scale structures, e.g., satellite images and biomedical images.