Semantic segmentation of Very High Resolution (VHR) remote sensing images is a fundamental task for many applications. However, large variations in the scales of objects in those VHR images pose a challenge for performing accurate semantic segmentation. Existing semantic segmentation networks are able to analyse an input image at up to four resizing scales, but this may be insufficient given the diversity of object scales. Therefore, Multi Scale (MS) test-time data augmentation is often used in practice to obtain more accurate segmentation results, which makes equal use of the segmentation results obtained at the different resizing scales. However, it was found in this study that different classes of objects had their preferred resizing scale for more accurate semantic segmentation. Based on this behaviour, a Stacking-Based Semantic Segmentation (SBSS) framework is proposed to improve the segmentation results by learning this behaviour, which contains a learnable Error Correction Module (ECM) for segmentation result fusion and an Error Correction Scheme (ECS) for computational complexity control. Two ECS, i.e., ECS-MS and ECS-SS, are proposed and investigated in this study. The Floating-point operations (Flops) required for ECS-MS and ECS-SS are similar to the commonly used MS test and the Single-Scale (SS) test, respectively. Extensive experiments on four datasets (i.e., Cityscapes, UAVid, LoveDA and Potsdam) show that SBSS is an effective and flexible framework. It achieved higher accuracy than MS when using ECS-MS, and similar accuracy as SS with a quarter of the memory footprint when using ECS-SS.

Explainability of Graph Neural Networks (GNNs) is critical to various GNN applications but remains an open challenge. A convincing explanation should be both necessary and sufficient simultaneously. However, existing GNN explaining approaches focus on only one of the two aspects, necessity or sufficiency, or a trade-off between the two. To search for the most necessary and sufficient explanation, the Probability of Necessity and Sufficiency (PNS) can be applied since it can mathematically quantify the necessity and sufficiency of an explanation. Nevertheless, the difficulty of obtaining PNS due to non-monotonicity and the challenge of counterfactual estimation limits its wide use. To address the non-identifiability of PNS, we resort to a lower bound of PNS that can be optimized via counterfactual estimation, and propose Necessary and Sufficient Explanation for GNN (NSEG) via optimizing that lower bound. Specifically, we employ nearest neighbor matching to generate counterfactual samples for the features, which is different from the random perturbation. In particular, NSEG combines the edges and node features to generate an explanation, where the common edge explanation is a special case of the combined explanation. Empirical study shows that NSEG achieves excellent performance in generating the most necessary and sufficient explanations among a series of state-of-the-art methods.

Recent studies have shown that CLIP has achieved remarkable success in performing zero-shot inference while its fine-tuning performance is not satisfactory. In this paper, we identify that fine-tuning performance is significantly impacted by hyper-parameter choices. We examine various key hyper-parameters and empirically evaluate their impact in fine-tuning CLIP for classification tasks through a comprehensive study. We find that the fine-tuning performance of CLIP is substantially underestimated. Equipped with hyper-parameter refinement, we demonstrate CLIP itself is better or at least competitive in fine-tuning compared with large-scale supervised pre-training approaches or latest works that use CLIP as prediction targets in Masked Image Modeling. Specifically, CLIP ViT-Base/16 and CLIP ViT-Large/14 can achieve 85.7%,88.0% finetuning Top-1 accuracy on the ImageNet-1K dataset . These observations challenge the conventional conclusion that CLIP is not suitable for fine-tuning, and motivate us to rethink recently proposed improvements based on CLIP. We will release our code publicly at \url{https://github.com/LightDXY/FT-CLIP}.

Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training data for free and significantly boosts the segmentation performance, especially for rare object categories. Although diverse, high-quality object instances used in Copy-Paste result in more performance gain, previous works utilize object instances either from human-annotated instance segmentation datasets or rendered from 3D object models, and both approaches are too expensive to scale up to obtain good diversity. In this paper, we revisit Copy-Paste at scale with the power of newly emerged zero-shot recognition models (e.g., CLIP) and text2image models (e.g., StableDiffusion). We demonstrate for the first time that using a text2image model to generate images or zero-shot recognition model to filter noisily crawled images for different object categories is a feasible way to make Copy-Paste truly scalable. To make such success happen, we design a data acquisition and processing framework, dubbed "X-Paste", upon which a systematic study is conducted. On the LVIS dataset, X-Paste provides impressive improvements over the strong baseline CenterNet2 with Swin-L as the backbone. Specifically, it archives +2.6 box AP and +2.1 mask AP gains on all classes and even more significant gains with +6.8 box AP +6.5 mask AP on long-tail classes.

Neural network pruning has been a well-established compression technique to enable deep learning models on resource-constrained devices. The pruned model is usually specialized to meet specific hardware platforms and training tasks (defined as deployment scenarios). However, existing pruning approaches rely heavily on training data to trade off model size, efficiency, and accuracy, which becomes ineffective for federated learning (FL) over distributed and confidential datasets. Moreover, the memory- and compute-intensive pruning process of most existing approaches cannot be handled by most FL devices with resource limitations. In this paper, we develop FedTiny, a novel distributed pruning framework for FL, to obtain specialized tiny models for memory- and computing-constrained participating devices with confidential local data. To alleviate biased pruning due to unseen heterogeneous data over devices, FedTiny introduces an adaptive batch normalization (BN) selection module to adaptively obtain an initially pruned model to fit deployment scenarios. Besides, to further improve the initial pruning, FedTiny develops a lightweight progressive pruning module for local finer pruning under tight memory and computational budgets, where the pruning policy for each layer is gradually determined rather than evaluating the overall deep model structure. Extensive experimental results demonstrate the effectiveness of FedTiny, which outperforms state-of-the-art baseline approaches, especially when compressing deep models to extremely sparse tiny models.

Cone beam computed tomography (CBCT) has been widely used in clinical practice, especially in dental clinics, while the radiation dose of X-rays when capturing has been a long concern in CBCT imaging. Several research works have been proposed to reconstruct high-quality CBCT images from sparse-view 2D projections, but the current state-of-the-arts suffer from artifacts and the lack of fine details. In this paper, we propose SNAF for sparse-view CBCT reconstruction by learning the neural attenuation fields, where we have invented a novel view augmentation strategy to overcome the challenges introduced by insufficient data from sparse input views. Our approach achieves superior performance in terms of high reconstruction quality (30+ PSNR) with only 20 input views (25 times fewer than clinical collections), which outperforms the state-of-the-arts. We have further conducted comprehensive experiments and ablation analysis to validate the effectiveness of our approach.

本文提出了一种基于中风的新型渲染方法（SBR）方法，该方法将图像转化为生动的油画。以前的SBR技术通常将油画问题作为像素近似。与这种技术路线不同，我们将油漆的创造视为一种自适应抽样问题。首先，我们根据输入图像的纹理复杂性计算概率密度图。然后，我们使用Voronoi算法将一组像素作为中风锚进行采样。接下来，我们在每个锚点上搜索并生成一个单独的石油冲程。最后，我们将所有笔触都放在画布上以获取油画。通过调整高参数的最大抽样概率，我们可以以线性方式控制油漆的细度。与现有的最先进的油画技术进行比较表明，我们的结果具有更高的保真度和更现实的纹理。用户意见测试表明，与其他方法的结果相比，人们对我们的油画的行为更加偏爱。更有趣的结果和代码在https://github.com/tzysjtu/im2oil中。

深度学习取得了长足的进步，用于图像中的对象检测。对象检测的检测准确性和计算成本取决于图像的空间分辨率，这可能会受到相机和存储注意事项的约束。压缩通常是通过减少空间或幅度分辨率或有时两者都对性能的众所周知的影响来实现的。检测精度还取决于感兴趣的对象与摄像机的距离。我们的工作研究了空间和振幅分辨率以及对象距离对物体检测准确性和计算成本的影响。我们开发了Yolov5（ra-Yolo）的分辨率 - 自适应变体，该变体基于输入图像的空间分辨率，它在特征金字塔和检测头中变化。为了训练和评估这种新方法，我们通过结合TJU和Eurocity数据集的图像来创建具有不同空间和振幅分辨率的图像数据集，并通过应用空间调整和压缩来生成不同的分辨率。我们首先表明Ra-Yolo在各种空间分辨率上实现了检测准确性和推理时间之间的良好权衡。然后，我们使用拟议的RA-YOLO模型评估空间和振幅分辨率对物体检测准确性的影响。我们证明，导致最高检测精度的最佳空间分辨率取决于“耐受性”图像大小。我们进一步评估了对象到摄像机对检测准确性的影响，并表明较高的空间分辨率可实现更大的检测范围。这些结果为选择图像空间分辨率和压缩设置提供了重要的指南，这些分辨率和压缩设置基于可用的带宽，存储，所需的推理时间和/或所需的检测范围，在实际应用中。

本文提出了一个简单而有效的框架蒙版，该框架将新提出的掩盖自distillation纳入对比的语言图像预处理中。掩盖自distillation的核心思想是将表示从完整的图像提取到蒙版图像预测的表示形式。这种合并享有两个重要的好处。首先，掩盖的自我验证目标是本地贴片表示学习，这与视觉对比度的互补，专注于与文本相关的表示。二，掩盖的自我验证也与视觉语言对比符合训练目标的视野对比是一致的。视觉编码器用于功能对齐，因此能够学习本地语义从该语言中获得间接监督。我们提供了专门设计的实验，并进行了全面的分析，以验证这两个好处。从经验上讲，我们表明，当MaskClip应用于各种具有挑战性的下游任务时，可以在线性探测，填充和零拍摄中取得卓越的结果，并在语言编码器的指导下取得了卓越的结果。

估计到达时间（ETA）预测时间（也称为旅行时间估计）是针对各种智能运输应用程序（例如导航，路线规划和乘车服务）的基本任务。为了准确预测一条路线的旅行时间，必须考虑到上下文和预测因素，例如空间 - 周期性的互动，驾驶行为和交通拥堵传播的推断。先前在百度地图上部署的ETA预测模型已经解决了时空相互作用（constgat）和驾驶行为（SSML）的因素。在这项工作中，我们专注于建模交通拥堵传播模式以提高ETA性能。交通拥堵的传播模式建模具有挑战性，它需要考虑到随着时间的推移影响区域的影响区域，以及延迟变化随时间变化的累积影响，这是由于道路网络上的流量事件引起的。在本文中，我们提出了一个实用的工业级ETA预测框架，名为Dueta。具体而言，我们基于交通模式的相关性构建了一个对拥堵敏感的图，并开发了一种路线感知图形变压器，以直接学习路段的长距离相关性。该设计使Dueta能够捕获空间遥远但与交通状况高度相关的路段对之间的相互作用。广泛的实验是在从百度地图收集的大型现实世界数据集上进行的。实验结果表明，ETA预测可以从学习的交通拥堵传播模式中显着受益。此外，Dueta已经在Baidu Maps的生产中部署，每天都有数十亿个请求。这表明Dueta是用于大规模ETA预测服务的工业级和强大的解决方案。