TransNeXt: Robust Foveal Visual Perception for Vision Transformers

TL;DR

TransNeXt introduces a novel vision transformer backbone that mimics biological foveal vision, avoiding depth degradation issues and achieving state-of-the-art performance on multiple vision tasks.

Contribution

The paper proposes Aggregated Attention and Convolutional GLU, enabling effective global and local perception without stacking layers, leading to a robust and efficient vision transformer architecture.

Findings

TransNeXt surpasses ConvNeXt with 69% fewer parameters at ImageNet-1K.

Achieves 86.2% ImageNet accuracy at 384^2 resolution.

Demonstrates superior performance on object detection and segmentation tasks.

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 learnable tokens that interact with conventional queries and keys, which further diversifies the generation of affinity matrices beyond merely relying on the similarity between queries and keys. Our approach does not rely on stacking for information exchange, thus effectively avoiding depth degradation and achieving natural visual perception. Additionally, we propose Convolutional GLU, a channel mixer that bridges the gap between GLU and SE mechanism, which empowers each token to have channel attention based on its nearest neighbor image features, enhancing local modeling capability and model robustness. We combine aggregated attention and convolutional GLU to create a new visual backbone called TransNeXt. Extensive experiments demonstrate that our TransNeXt achieves state-of-the-art performance across multiple model sizes. At a resolution of $224^2$, TransNeXt-Tiny attains an ImageNet accuracy of 84.0%, surpassing ConvNeXt-B with 69% fewer parameters. Our TransNeXt-Base achieves an ImageNet accuracy of 86.2% and an ImageNet-A accuracy of 61.6% at a resolution of $384^2$, a COCO object detection mAP of 57.1, and an ADE20K semantic segmentation mIoU of 54.7.