Recently, lightweight Vision Transformers (ViTs) demonstrate superior
performance and lower latency compared with lightweight Convolutional Neural
Networks (CNNs) on resource-constrained mobile devices. This improvement is
usually attributed to the multi-head self-attention module, which enables the
model to learn global representations. However, the architectural disparities
between lightweight ViTs and lightweight CNNs have not been adequately
examined. In this study, we revisit the efficient design of lightweight CNNs
and emphasize their potential for mobile devices. We incrementally enhance the
mobile-friendliness of a standard lightweight CNN, specifically MobileNetV3, by
integrating the efficient architectural choices of lightweight ViTs. This ends
up with a new family of pure lightweight CNNs, namely RepViT. Extensive
experiments show that RepViT outperforms existing state-of-the-art lightweight
ViTs and exhibits favorable latency in various vision tasks. On ImageNet,
RepViT achieves over 80\% top-1 accuracy with nearly 1ms latency on an iPhone
12, which is the first time for a lightweight model, to the best of our
knowledge. Our largest model, RepViT-M3, obtains 81.4\% accuracy with only
1.3ms latency. The code and trained models are available at
https://github.com/jameslahm/RepViT.

轻量级视觉变换器（ViTs）相较于资源受限的移动设备上的轻量级卷积神经网络（CNNs），通过多头自注意模块获得更高的性能和更低的延迟。本研究回顾了轻量级 CNNs 的高效设计，强调其在移动设备上的潜力，并通过整合轻量级 ViTs 的高效架构选择增强了一种新的纯轻量级 CNNs 家族，即 RepViT。大量实验证明，RepViT 优于现有的轻量级 ViTs，并在各种视觉任务中具有有利的延迟。在 ImageNet 上，RepViT 在 iPhone 12 上实现了超过 80％的 top-1 准确性，延迟接近 1 毫秒，这在我们的知识范围内是轻量级模型的首次。我们最大的模型 RepViT-M3 在仅 1.3 毫秒延迟下获得了 81.4％的准确性。代码和训练模型可在 https://github.com/jameslahm/RepViT 找到。

RepViT：从 ViT 的视角重新审视移动 CNN

RepViT: Revisiting Mobile CNN From ViT Perspective

We present a new data-driven approach with physics-based priors to
scene-level normal estimation from a single polarization image. Existing shape
from polarization (SfP) works mainly focus on estimating the normal of a single
object rather than complex scenes in the wild. A key barrier to high-quality
scene-level SfP is the lack of real-world SfP data in complex scenes. Hence, we
contribute the first real-world scene-level SfP dataset with paired input
polarization images and ground-truth normal maps. Then we propose a
learning-based framework with a multi-head self-attention module and viewing
encoding, which is designed to handle increasing polarization ambiguities
caused by complex materials and non-orthographic projection in scene-level SfP.
Our trained model can be generalized to far-field outdoor scenes as the
relationship between polarized light and surface normals is not affected by
distance. Experimental results demonstrate that our approach significantly
outperforms existing SfP models on two datasets. Our dataset and source code
will be publicly available at this https URL

该研究提出了一种新的基于数据驱动和物理学先验信息的场景级别单极化图像法线估计方法，并且建立了第一个真实场景级别形态恢复数据集。该方法采用了多头自注意力与视图编码来处理在野外环境中形成的极化杂波和联机投影问题，实验结果表明，相对于现有的形态恢复方法，该方法具有更好的性能。