2022/11/10 by Steven Walton, Ali Hassani, Walton, Steven +7 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image Retrieval and Classification Techniques #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2211.05770
openalex publication_date 2022/11/10 · openalex created_date 2022/11/16 · openalex updated_date 2026/07/28
While the integration of transformers in vision models have yielded significant improvements on vision tasks they still require significant amounts of computation for both training and inference. Restricted attention mechanisms significantly reduce these computational burdens but come at the cost of losing either global or local coherence. We propose a simple, yet powerful method to reduce these trade-offs: allow the attention heads of a single transformer to attend to multiple receptive fields. We demonstrate our method utilizing Neighborhood Attention (NA) and integrate it into a StyleGAN based architecture for image generation. With this work, dubbed StyleNAT, we are able to achieve a FID of 2.05 on FFHQ, a 6% improvement over StyleGAN-XL, while utilizing 28% fewer parameters and with 4× the throughput capacity. StyleNAT achieves the Pareto Frontier on FFHQ-256 and demonstrates powerful and efficient image generation on other datasets. Our code and model checkpoints are publicly available at: https://github.com/SHI-Labs/StyleNAT