AI Frontier Lectures
Apr 8, 2025 · Artificial Intelligence
How HINT’s Hierarchical Multi‑Head Attention Boosts Image Restoration
The article introduces HINT, a Transformer‑based image restoration model that solves the redundancy of standard multi‑head attention by using Hierarchical Multi‑Head Attention and a Query‑Key Cache Updating module, and demonstrates superior PSNR/SSIM performance across multiple low‑level vision tasks while keeping model complexity low.
Deep Learningquery-key cache
0 likes · 10 min read
