AIBullisharXiv – CS AI · Mar 56/10
🧠
Separators in Enhancing Autoregressive Pretraining for Vision Mamba
Researchers introduce STAR, a new autoregressive pretraining method for Vision Mamba that uses separators to quadruple input sequence length while maintaining image dimensions. The STAR-B model achieved 83.5% accuracy on ImageNet-1k, demonstrating improved performance through better utilization of long-range dependencies in computer vision tasks.