Untrained Physics-based Deep Learning (DL) methods for digital holography
have gained significant attention due to their benefits, such as not requiring
an annotated training dataset, and providing interpretability since utilizing
the governing laws of hologram formation. However, they are sensitive to the
hard-to-obtain precise object distance from the imaging plane, posing the
$\textit{Autofocusing}$ challenge. Conventional solutions involve
reconstructing image stacks for different potential distances and applying
focus metrics to select the best results, which apparently is computationally
inefficient. In contrast, recently developed DL-based methods treat it as a
supervised task, which again needs annotated data and lacks generalizability.
To address this issue, we propose $\textit{reverse-attention loss}$, a weighted
sum of losses for all possible candidates with learnable weights. This is a
pioneering approach to addressing the Autofocusing challenge in untrained
deep-learning methods. Both theoretical analysis and experiments demonstrate
its superiority in efficiency and accuracy. Interestingly, our method presents
a significant reconstruction performance over rival methods (i.e. alternating
descent-like optimization, non-weighted loss integration, and random distance
assignment) and even is almost equal to that achieved with a precisely known
object distance. For example, the difference is less than 1dB in PSNR and 0.002
in SSIM for the target sample in our experiment.

提出了一种解决无训练深度学习方法中自动对焦挑战的创新方法，基于物理学原理的数字全息图像重建，通过可学习权重的反向关注损失取得了更高的效率和准确性。

利用反向注意损失增强数字全息图重建的未经训练的基于物理驱动的深度学习模型，对于具有不确定距离的情况

Enhancing Digital Hologram Reconstruction Using Reverse-Attention Loss  for Untrained Physics-Driven Deep Learning Models with Uncertain Distance

Recent years have witnessed the great success of vision transformer (ViT),
which has achieved state-of-the-art performance on multiple computer vision
benchmarks. However, ViT models suffer from vast amounts of parameters and high
computation cost, leading to difficult deployment on resource-constrained edge
devices. Existing solutions mostly compress ViT models to a compact model but
still cannot achieve real-time inference. To tackle this issue, we propose to
explore the divisibility of transformer structure, and decompose the large ViT
into multiple small models for collaborative inference at edge devices. Our
objective is to achieve fast and energy-efficient collaborative inference while
maintaining comparable accuracy compared with large ViTs. To this end, we first
propose a collaborative inference framework termed DeViT to facilitate edge
deployment by decomposing large ViTs. Subsequently, we design a
decomposition-and-ensemble algorithm based on knowledge distillation, termed
DEKD, to fuse multiple small decomposed models while dramatically reducing
communication overheads, and handle heterogeneous models by developing a
feature matching module to promote the imitations of decomposed models from the
large ViT. Extensive experiments for three representative ViT backbones on four
widely-used datasets demonstrate our method achieves efficient collaborative
inference for ViTs and outperforms existing lightweight ViTs, striking a good
trade-off between efficiency and accuracy. For example, our DeViTs improves
end-to-end latency by 2.89$\times$ with only 1.65% accuracy sacrifice using
CIFAR-100 compared to the large ViT, ViT-L/16, on the GPU server. DeDeiTs
surpasses the recent efficient ViT, MobileViT-S, by 3.54% in accuracy on
ImageNet-1K, while running 1.72$\times$ faster and requiring 55.28% lower
energy consumption on the edge device.

最近的研究已经取得了视觉转换器 (ViT) 的巨大成功，在多个计算机视觉基准测试中取得了最先进的性能。然而，ViT 模型受到庞大的参数量和高计算成本的限制，导致在资源受限的边缘设备上难以部署。为了解决这个问题，我们提出了一种探索转换器结构的可拆分性，将大型 ViT 分解成多个小型模型，在边缘设备上进行协同推理。我们的目标是实现快速高效的协同推理，并与大型 ViTs 相比保持相当的准确性。为此，我们首先提出了一种名为 DeViT 的协同推理框架，通过分解大型 ViTs 来促进边缘部署。随后，我们设计了一种基于知识蒸馏的分解和集成算法，称为 DEKD，通过开发特征匹配模块来处理异构模型，以促进从大型 ViT 中分解出的模型的模仿能力。在四个广泛使用的数据集上对三个代表性的 ViT 骨干部分进行了大量实验证明我们的方法实现了 ViTs 的高效协同推理，并且优于现有的轻量级 ViTs，在效率和准确性之间取得了良好的平衡。例如，在 GPU 服务器上使用 CIFAR-100，与大型 ViT，ViT-L/16 相比，我们的 DeViTs 可以通过牺牲 1.65% 的准确性来提高端到端延迟 2.89 倍。DeDeiTs 在 ImageNet-1K 上的准确性超过了最近的高效 ViT，MobileViT-S，同时运行速度提升了 1.72 倍，边缘设备的能源消耗降低了 55.28%。

DeViT：分解视觉 Transformer 用于边缘设备的协同推理

DeViT: Decomposing Vision Transformers for Collaborative Inference in  Edge Devices

In this paper, we empirically study how to make the most of low-resolution
frames for efficient video recognition. Existing methods mainly focus on
developing compact networks or alleviating temporal redundancy of video inputs
to increase efficiency, whereas compressing frame resolution has rarely been
considered a promising solution. A major concern is the poor recognition
accuracy on low-resolution frames. We thus start by analyzing the underlying
causes of performance degradation on low-resolution frames. Our key finding is
that the major cause of degradation is not information loss in the
down-sampling process, but rather the mismatch between network architecture and
input scale. Motivated by the success of knowledge distillation (KD), we
propose to bridge the gap between network and input size via cross-resolution
KD (ResKD). Our work shows that ResKD is a simple but effective method to boost
recognition accuracy on low-resolution frames. Without bells and whistles,
ResKD considerably surpasses all competitive methods in terms of efficiency and
accuracy on four large-scale benchmark datasets, i.e., ActivityNet, FCVID,
Mini-Kinetics, Something-Something V2. In addition, we extensively demonstrate
its effectiveness over state-of-the-art architectures, i.e., 3D-CNNs and Video
Transformers, and scalability towards super low-resolution frames. The results
suggest ResKD can serve as a general inference acceleration method for
state-of-the-art video recognition. Our code will be available at
this https URL

本研究通过跨分辨率知识蒸馏方法（ResKD）来解决在低分辨率视频帧上识别准确度低的问题，该方法证明了在提高效率和精度方面的有效性，并可扩展到极低分辨率帧。