TransNeXt: Robust Foveal Visual Perception for Vision Transformers

arXiv:2311.17132v2 Announce Type: replace
Abstract: Due to the depth degradation effect in residual connections, many efficient Vision Transformers models that rely on stacking layers for information exchange often fail to form sufficient information mixing, leading to unnatural visual perception. To address this issue, in this paper, we propose Aggregated Attention, a biomimetic design-based token mixer that simulates biological foveal vision and continuous eye movement while enabling each token on the feature map to have a global perception. Furthermore, we incorporate …

abstract arxiv attention cs.ai cs.cv form information issue paper perception residual robust transformers type vision vision transformers visual