Pattern recognition and classification

POSITION-AWARE GRAPH-BASED LEARNING OF WHOLE SLIDE IMAGES

A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning

A Probabilistic Framework for Pruning Transformers via a Finite Admixture of Keys

Asynchronous Federated Learning for Real-time Multiple Licence Plate Recognition through Semantic Communication

Image Reconstruction Without Explicit Priors

Hierarchical Multi-Task Learning for Fabric Component Analysis Based on NIR Spectral Signals

Learn Topological Representation with Flexible Manifold Layer

Backdoor Defense via Suppressing Model Shortcuts

Exploiting One-class classification optimization objectives for increasing adversarial robustness

Provably Convergent Plug & Play Linearized ADMM, applied to Deblurring Spatially Varying Kernels

Building Blocks for a Complex-Valued Transformer Architecture

Untargeted Backdoor Attack against Object Detection