Vision Transformers Comparison Hub
4 papers - avg viability 6.5
Top Papers
- CAViT -- Channel-Aware Vision Transformer for Dynamic Feature Fusion(7.0)
CAViT enhances Vision Transformers with dynamic channel-wise attention for superior and efficient image analysis.
- Adaptive MLP Pruning for Large Vision Transformers(7.0)
Adaptively prune large vision transformers' MLP layers to reduce parameters and FLOPs by 40% without significant performance loss, offering a more efficient model deployment.
- Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data(6.0)
A framework for Vision Transformers offering superior performance in limited label scenarios by using semi-supervised masked autoencoding and pseudo-labels.
- HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers(6.0)
HiAP is an innovative framework that optimizes Vision Transformers for efficient deployment on edge devices through multi-granular stochastic pruning.