Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in graph, their ST patterns can vary greatly in difficulties for modeling, owning to the heterogeneous nature of ST data. We argue that unveiling the nodes to the model in a meaningful order, from easy to complex, can provide performance improvements over traditional training procedure. The idea has its root in Curriculum Learning which suggests in the early stage of training models can be sensitive to noise and difficult samples. In this paper, we propose ST-Curriculum Dropout, a novel and easy-to-implement strategy for spatial-temporal graph modeling. Specifically, we evaluate the learning difficulty of each node in high-level feature space and drop those difficult ones out to ensure the model only needs to handle fundamental ST relations at the beginning, before gradually moving to hard ones. Our strategy can be applied to any canonical deep learning architecture without extra trainable parameters, and extensive experiments on a wide range of datasets are conducted to illustrate that, by controlling the difficulty level of ST relations as the training progresses, the model is able to capture better representation of the data and thus yields better generalization.

Despite high global prevalence of hepatic steatosis, no automated diagnostics demonstrated generalizability in detecting steatosis on multiple international datasets. Traditionally, hepatic steatosis detection relies on clinicians selecting the region of interest (ROI) on computed tomography (CT) to measure liver attenuation. ROI selection demands time and expertise, and therefore is not routinely performed in populations. To automate the process, we validated an existing artificial intelligence (AI) system for 3D liver segmentation and used it to purpose a novel method: AI-ROI, which could automatically select the ROI for attenuation measurements. AI segmentation and AI-ROI method were evaluated on 1,014 non-contrast enhanced chest CT images from eight international datasets: LIDC-IDRI, NSCLC-Lung1, RIDER, VESSEL12, RICORD-1A, RICORD-1B, COVID-19-Italy, and COVID-19-China. AI segmentation achieved a mean dice coefficient of 0.957. Attenuations measured by AI-ROI showed no significant differences (p = 0.545) and a reduction of 71% time compared to expert measurements. The area under the curve (AUC) of the steatosis classification of AI-ROI is 0.921 (95% CI: 0.883 - 0.959). If performed as a routine screening method, our AI protocol could potentially allow early non-invasive, non-pharmacological preventative interventions for hepatic steatosis. 1,014 expert-annotated liver segmentations of patients with hepatic steatosis annotations can be downloaded here: https://drive.google.com/drive/folders/1-g_zJeAaZXYXGqL1OeF6pUjr6KB0igJX.

免疫组织化学染色图像的可靠定量分析需要准确稳健的细胞检测和分类。最近的弱监督方法通常估计细胞识别的概率密度图。但是，在密集的细胞场景中，由于无法找到通用参数设置，因此可以通过预处理和后处理受到限制。在本文中，我们引入了一个端到端框架，该框架应用了预设锚点的直接回归和分类。具体而言，我们提出了一种锥体特征聚合策略，可以同时组合低级特征和高级语义，该策略为我们的纯粹基于点的模型提供了准确的细胞识别。此外，优化的成本功能旨在通过匹配地面真相和预测点来调整我们的多任务学习框架。实验结果证明了所提出的方法的卓越准确性和效率，这揭示了辅助病理学家评估的很大潜力。

核分型是评估染色体异常可能存在的重要程序。但是，由于非刚性性质，染色体通常在微观图像中弯曲，这种变形形状阻碍了细胞遗传学家的染色体分析。在本文中，我们提出了一个自我发项的指导框架，以消除染色体的曲率。提出的框架提取空间信息和本地纹理，以在回归模块中保留带模式。借助弯曲染色体的互补信息，改进模块旨在进一步改善细节。此外，我们提出了两个专用的几何约束，以维持长度并恢复染色体的变形。为了训练我们的框架，我们创建一个合成数据集，其中通过网格变形从现实世界的直染色体生成弯曲的染色体。定量和定性实验是对合成和现实世界数据进行的。实验结果表明，我们所提出的方法可以有效拉直弯曲的染色体，同时保持带的细节和长度。

分布（OOD）检测是安全部署模型在开放世界中的关键。对于OOD检测，收集足够的标记数据（ID）通常比未标记的数据更耗时且昂贵。当ID标记的数据受到限制时，由于其对ID标记的数据的量的高度依赖性，因此先前的OOD检测方法不再优越。基于有限的ID标记数据和足够的未标记数据，我们定义了一种称为弱监督的新设置（WSOOD）。为了解决新问题，我们提出了一种称为拓扑结构学习（TSL）的有效方法。首先，TSL使用一种对比度学习方法来构建ID和OOD数据的初始拓扑结构空间。其次，在初始拓扑空间中，TSL矿山有效的拓扑连接。最后，基于有限的ID标记数据和开采拓扑连接，TSL在新的拓扑空间中重建拓扑结构，以提高ID和OOD实例的可分离性。对几个代表性数据集的广泛研究表明，TSL明显胜过最先进的研究，从而在新的WSood环境中验证了我们方法的有效性和鲁棒性。

滚动快门（RS）失真可以解释为在RS摄像机曝光期间，随着时间的推移从瞬时全局快门（GS）框架中挑选一排像素。这意味着每个即时GS帧的信息部分，依次是嵌入到行依赖性失真中。受到这一事实的启发，我们解决了扭转这一过程的挑战性任务，即从rs失真中的图像中提取未变形的GS框架。但是，由于RS失真与其他因素相结合，例如读数设置以及场景元素与相机的相对速度，因此仅利用临时相邻图像之间的几何相关性的型号，在处理数据中，具有不同的读数设置和动态场景的数据中遭受了不良的通用性。带有相机运动和物体运动。在本文中，我们建议使用双重RS摄像机捕获的一对图像，而不是连续的框架，而RS摄像机则具有相反的RS方向，以完成这项极具挑战性的任务。基于双重反转失真的对称和互补性，我们开发了一种新型的端到端模型，即IFED，以通过卢比时间对速度场的迭代学习来生成双重光流序列。广泛的实验结果表明，IFED优于天真的级联方案，以及利用相邻RS图像的最新艺术品。最重要的是，尽管它在合成数据集上进行了训练，但显示出在从现实世界中的RS扭曲的动态场景图像中检索GS框架序列有效。代码可在https://github.com/zzh-tech/dual-versed-rs上找到。

标签噪声显着降低了应用中深度模型的泛化能力。有效的策略和方法，\ Texit {例如}重新加权或损失校正，旨在在训练神经网络时缓解标签噪声的负面影响。这些现有的工作通常依赖于预指定的架构并手动调整附加的超参数。在本文中，我们提出了翘曲的概率推断（WARPI），以便在元学习情景中自适应地整理分类网络的培训程序。与确定性模型相比，WARPI通过学习摊销元网络来制定为分层概率模型，这可以解决样本模糊性，因此对严格的标签噪声更加坚固。与直接生成损耗的重量值的现有近似加权功能不同，我们的元网络被学习以估计从登录和标签的输入来估计整流向量，这具有利用躺在它们中的足够信息的能力。这提供了纠正分类网络的学习过程的有效方法，证明了泛化能力的显着提高。此外，可以将整流载体建模为潜在变量并学习元网络，可以无缝地集成到分类网络的SGD优化中。我们在嘈杂的标签上评估了四个强大学习基准的Warpi，并在变体噪声类型下实现了新的最先进的。广泛的研究和分析还展示了我们模型的有效性。

Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.