准确，快速的双核细胞（BC）检测在预测白血病和其他恶性肿瘤的风险中起着重要作用。但是，手动显微镜计数是耗时的，缺乏客观性。此外，由于bc显微镜整体幻灯片图像（WSIS）的染色质量和多样性的限制，传统的图像处理方法是无助的。为了克服这一挑战，我们提出了一种基于深度学习的结构启发的两阶段检测方法，该方法是基于深度学习的，该方法是在斑块级别的WSI-Level和细粒度分类处实施BCS粗略检测的级联。粗糙检测网络是基于用于细胞检测的圆形边界框的多任务检测框架，以及用于核检测的中心关键点。圆的表示降低了自由度，与通常的矩形盒子相比，减轻周围杂质的影响，并且在WSI中可能是旋转不变的。检测细胞核中的关键点可以帮助网络感知，并在后来的细粒分类中用于无监督的颜色层分割。精细的分类网络由基于颜色层掩模的监督和基于变压器的关键区域选择模块组成的背景区域抑制模块，其全局建模能力。此外，首先提出了无监督和未配对的细胞质发生器网络来扩展长尾分配数据集。最后，在BC多中心数据集上进行实验。拟议的BC罚款检测方法在几乎所有评估标准中都优于其他基准，从而为诸如癌症筛查等任务提供了澄清和支持。

扩展方法探讨了深度学习方法中输入长度中性能瓶颈的可能性。在这项工作中，我们介绍了块静态扩展，该块静态扩展分布和处理输入，以与输入相比，以不同长度为特征的异质和任意大的序列集合。从这种方法中，我们引入了一种名为AspectionNet V2的新模型，该模型使用我们的新培训策略进行了培训，该模型不仅具有有效性，而且与最近的图像字幕中的标准方法相比，它的效率不仅快6倍。我们的新模型在MS-Coco 2014字幕挑战上实现了最先进的表现，在离线测试拆分中得分为143.7 Cider-D，在线评估服务器中的140.8 Cider-D和NoCaps验证集中的72.9 All-Cider。源代码可用：https：//github.com/jchenghu/expansionnet_v2

最新的艺术结构状态依赖于三种方法的组合和变化：卷积，经常性和自我牵键方法。我们的工作试图根据修改序列长度的想法为序列建模的新研究方向奠定基础。为此，我们提出了一种称为``扩展机制''的新方法，该方法将输入序列动态转换为具有不同序列长度的新方法。此外，我们引入了一种新颖的体系结构，可利用这种方法并在MS-COCO 2014数据集上实现竞争性能，在合奏和单个模型配置中分别在karpathy测试中产生134.6和131.4 Cider-d，在单个模型配置中分配和130 Cider-D和130 Cider-d官方的在线测试服务器既不反复出现也不完全专注。同时，我们解决了设计中的效率方面，并引入了适合大多数计算资源的方便培训策略，与标准资源相比。源代码可从https://github.com/jchenghu/expansionnet获得

图形神经网络（GNNS）已经变得越来越流行，并且在许多基于图形的应用程序中实现了令人印象深刻的结果。但是，需要广泛的手动工作和域知识来设计有效的架构，GNN模型的结果具有高差异，与不同的培训设置相比，限制了现有GNN模型的应用。在本文中，我们展示了AutoHensgnn，这是一个框架，用于为图表任务构建有效和强大的模型而没有任何人为干预。 Autohensgnn在kdd杯2020年签名挑战中赢得了第一名，并在最终阶段实现了五个现实生活数据集的最佳等级分数。鉴于任务，AutoHensgnn首先应用一个快速的代理评估，以自动选择有希望的GNN模型的池。然后它构建了一个分层合奏框架：1）我们提出图形自我合奏（GSE），这可以减少重量初始化的方差，有效利用本地和全球街区的信息; 2）基于GSE，使用不同类型的GNN模型的加权集合来有效地学习更多辨别节点表示。为了有效地搜索体系结构和合奏权重，我们提出了AutoHensgnn $ _ {\ text {梯度}} $，它将架构和集合权重视为架构参数，并使用基于梯度的架构搜索来获得最佳配置，而autohensgnn $ {autohensgnn $ { \文本{Adaptive}} $，可以根据模型精度自适应地调整集合重量。关于节点分类的广泛实验，图形分类，边缘预测和KDD杯挑战表明了Autohensgnn的有效性和一般性

Deep learning techniques have made considerable progress in image inpainting, restoration, and reconstruction in the last few years. Image outpainting, also known as image extrapolation, lacks attention and practical approaches to be fulfilled, owing to difficulties caused by large-scale area loss and less legitimate neighboring information. These difficulties have made outpainted images handled by most of the existing models unrealistic to human eyes and spatially inconsistent. When upsampling through deconvolution to generate fake content, the naive generation methods may lead to results lacking high-frequency details and structural authenticity. Therefore, as our novelties to handle image outpainting problems, we introduce structural prior as a condition to optimize the generation quality and a new semantic embedding term to enhance perceptual sanity. we propose a deep learning method based on Generative Adversarial Network (GAN) and condition edges as structural prior in order to assist the generation. We use a multi-phase adversarial training scheme that comprises edge inference training, contents inpainting training, and joint training. The newly added semantic embedding loss is proved effective in practice.

Recent years have witnessed the rapid progress of image captioning. However, the demands for large memory storage and heavy computational burden prevent these captioning models from being deployed on mobile devices. The main obstacles lie in the heavyweight visual feature extractors (i.e., object detectors) and complicated cross-modal fusion networks. To this end, we propose LightCap, a lightweight image captioner for resource-limited devices. The core design is built on the recent CLIP model for efficient image captioning. To be specific, on the one hand, we leverage the CLIP model to extract the compact grid features without relying on the time-consuming object detectors. On the other hand, we transfer the image-text retrieval design of CLIP to image captioning scenarios by devising a novel visual concept extractor and a cross-modal modulator. We further optimize the cross-modal fusion model and parallel prediction heads via sequential and ensemble distillations. With the carefully designed architecture, our model merely contains 40M parameters, saving the model size by more than 75% and the FLOPs by more than 98% in comparison with the current state-of-the-art methods. In spite of the low capacity, our model still exhibits state-of-the-art performance on prevalent datasets, e.g., 136.6 CIDEr on COCO Karpathy test split. Testing on the smartphone with only a single CPU, the proposed LightCap exhibits a fast inference speed of 188ms per image, which is ready for practical applications.

Graph neural networks (GNNs) are popular weapons for modeling relational data. Existing GNNs are not specified for attribute-incomplete graphs, making missing attribute imputation a burning issue. Until recently, many works notice that GNNs are coupled with spectral concentration, which means the spectrum obtained by GNNs concentrates on a local part in spectral domain, e.g., low-frequency due to oversmoothing issue. As a consequence, GNNs may be seriously flawed for reconstructing graph attributes as graph spectral concentration tends to cause a low imputation precision. In this work, we present a regularized graph autoencoder for graph attribute imputation, named MEGAE, which aims at mitigating spectral concentration problem by maximizing the graph spectral entropy. Notably, we first present the method for estimating graph spectral entropy without the eigen-decomposition of Laplacian matrix and provide the theoretical upper error bound. A maximum entropy regularization then acts in the latent space, which directly increases the graph spectral entropy. Extensive experiments show that MEGAE outperforms all the other state-of-the-art imputation methods on a variety of benchmark datasets.

Unsupervised image registration commonly adopts U-Net style networks to predict dense displacement fields in the full-resolution spatial domain. For high-resolution volumetric image data, this process is however resource intensive and time-consuming. To tackle this problem, we propose the Fourier-Net, replacing the expansive path in a U-Net style network with a parameter-free model-driven decoder. Specifically, instead of our Fourier-Net learning to output a full-resolution displacement field in the spatial domain, we learn its low-dimensional representation in a band-limited Fourier domain. This representation is then decoded by our devised model-driven decoder (consisting of a zero padding layer and an inverse discrete Fourier transform layer) to the dense, full-resolution displacement field in the spatial domain. These changes allow our unsupervised Fourier-Net to contain fewer parameters and computational operations, resulting in faster inference speeds. Fourier-Net is then evaluated on two public 3D brain datasets against various state-of-the-art approaches. For example, when compared to a recent transformer-based method, i.e., TransMorph, our Fourier-Net, only using 0.22$\%$ of its parameters and 6.66$\%$ of the mult-adds, achieves a 0.6\% higher Dice score and an 11.48$\times$ faster inference speed. Code is available at \url{https://github.com/xi-jia/Fourier-Net}.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

本文回顾了AIM 2022上压缩图像和视频超级分辨率的挑战。这项挑战包括两条曲目。轨道1的目标是压缩图像的超分辨率，轨迹〜2靶向压缩视频的超分辨率。在轨道1中，我们使用流行的数据集DIV2K作为培训，验证和测试集。在轨道2中，我们提出了LDV 3.0数据集，其中包含365个视频，包括LDV 2.0数据集（335个视频）和30个其他视频。在这一挑战中，有12支球队和2支球队分别提交了赛道1和赛道2的最终结果。所提出的方法和解决方案衡量了压缩图像和视频上超分辨率的最先进。提出的LDV 3.0数据集可在https://github.com/renyang-home/ldv_dataset上找到。此挑战的首页是在https://github.com/renyang-home/aim22_compresssr。