ATD: Improved Transformer With Adaptive Token Dictionary for Image Restoration

Researchers proposed Adaptive Token Dictionary (ATD), a new transformer architecture (a type of AI model good at learning relationships between different parts of data) designed to improve image restoration tasks like super-resolution and denoising while reducing computational demands. Unlike traditional transformers that struggle with high computational costs, ATD uses a learnable token dictionary (a set of learned patterns representing typical image structures) and a cross-attention mechanism (a way for the model to compare input data against these learned patterns) to achieve better performance with lower computational complexity.