Tracking objects over long videos effectively means solving a spectrum of problems, from short-term association for un-occluded objects to long-term association for objects that are occluded and then reappear in the scene. Methods tackling these two tasks are often disjoint and crafted for specific scenarios, and top-performing approaches are often a mix of techniques, which yields engineering-heavy solutions that lack generality. In this work, we question the need for hybrid approaches and introduce SUSHI, a unified and scalable multi-object tracker. Our approach processes long clips by splitting them into a hierarchy of subclips, which enables high scalability. We leverage graph neural networks to process all levels of the hierarchy, which makes our model unified across temporal scales and highly general. As a result, we obtain significant improvements over state-of-the-art on four diverse datasets. Our code and models will be made available.

图提供了一种自然的方式来制定多个对象跟踪（MOT）和多个对象跟踪和分割（MOTS），逐个检测范式中。但是，他们还引入了学习方法的主要挑战，因为定义可以在这种结构化领域运行的模型并不是微不足道的。在这项工作中，我们利用MOT的经典网络流程公式来定义基于消息传递网络（MPN）的完全微分框架。通过直接在图形域上操作，我们的方法可以在整个检测和利用上下文特征上全球推理。然后，它共同预测了数据关联问题的最终解决方案和场景中所有对象的分割掩码，同时利用这两个任务之间的协同作用。我们在几个公开可用的数据集中获得跟踪和细分的最新结果。我们的代码可在github.com/ocetintas/mpntrackseg上找到。

Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple different domains, and may not contain labels for training. Certain settings, for instance medical applications, often involve further restrictions that prohibit retention of previously seen data due to privacy regulations. In this work, to address such challenges, we study unsupervised segmentation in continual learning scenarios that involve domain shift. To that end, we introduce GarDA (Generative Appearance Replay for continual Domain Adaptation), a generative-replay based approach that can adapt a segmentation model sequentially to new domains with unlabeled data. In contrast to single-step unsupervised domain adaptation (UDA), continual adaptation to a sequence of domains enables leveraging and consolidation of information from multiple domains. Unlike previous approaches in incremental UDA, our method does not require access to previously seen data, making it applicable in many practical scenarios. We evaluate GarDA on two datasets with different organs and modalities, where it substantially outperforms existing techniques.

随机且未知的散射介质背后的对象的分类为计算成像和机器视野字段的具有挑战性的任务。最新的基于深度学习的方法证明了使用图像传感器收集的扩散器延伸模式对对象进行分类。这些方法需要使用在数字计算机上运行的深神经网络进行相对大规模的计算。在这里，我们提出了一个全光处理器，使用单个像素检测到的宽带照明通过未知的随机相扩散器直接对未知对象进行分类。使用深度学习进行了优化的一组传播衍射层，形成了一个物理网络，该物理网络全面地绘制了随机扩散器后面输入对象的空间信息，以进入通过单个像素在输出平面上检测到的输出光的功率谱，衍射网络。我们在数值上使用宽带辐射通过随机新扩散器对未知手写数字进行分类，在训练阶段从未使用过，并实现了88.53％的盲目测试准确性。这种通过随机扩散器的单像素全光对象分类系统基于被动衍射层，该层可以通过简单地缩放与波长范围的衍射范围来缩放衍射特征，从而在电磁光谱的任何部分中运行，并且可以在电磁光谱的任何部分工作。这些结果在例如生物医学成像，安全性，机器人技术和自动驾驶中具有各种潜在的应用。

多个实例学习（MIL）方法在数字病理学中对GIGA像素大小的全型图像（WSI）进行分类变得越来越流行。大多数MIL方法通过处理所有组织斑块，以单个WSI放大倍率运行。这样的公式诱导了高计算要求，并将WSI级表示的上下文化限制为单个量表。一些MIL方法扩展到多个量表，但在计算上要求更高。在本文中，受病理诊断过程的启发，我们提出了Zoommil，该方法学会了以端到端的方式执行多层缩放。Zoommil通过从多个增强元中汇总组织信息来构建WSI表示。所提出的方法在两个大数据集上的WSI分类中优于最先进的MIL方法，同时大大降低了关于浮点操作（FLOPS）和处理时间的计算需求，最高为40倍。

3D光学相干断层扫描图像中视网膜流体的准确分割是诊断和个性化眼部疾病的关键。尽管深度学习在这项任务上取得了成功，但受过训练的监督模型通常会因不像标记示例的图像而失败，例如对于使用不同设备获取的图像。我们在此提出了一个新型的半监督学习框架，用于从新未标记的域分割体积图像。我们共同使用受监督和对比度学习，还引入了一种对比配对方案，该方案利用3D中附近切片之间的相似性。此外，我们建议通过渠道聚合作为对比特征图投影的常规空间释放聚合的替代方法。我们评估了从（标记的）源域对（未标记的）目标域的域适应方法，每个方法都包含具有不同采集设备的图像。在目标域中，我们的方法获得了比SIMCLR（最先进的对比框架）高13.8％的骰子系数，并导致结果可与该领域中有监督的训练的上限相当。在源域中，我们的模型还通过成功利用来自许多未标记的图像的信息，将结果提高了5.4％。

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the training on subsequent tasks. However, this is not always possible, e.g., due to data protection regulations. In such restricted scenarios, one can employ generative models to replay either artificial images or hidden features to a classifier. In this work, we propose Genifer (GENeratIve FEature-driven image Replay), where a generative model is trained to replay images that must induce the same hidden features as real samples when they are passed through the classifier. Our technique therefore incorporates the benefits of both image and feature replay, i.e.: (1) unlike conventional image replay, our generative model explicitly learns the distribution of features that are relevant for classification; (2) in contrast to feature replay, our entire classifier remains trainable; and (3) we can leverage image-space augmentations, which increase distillation performance while also mitigating overfitting during the training of the generative model. We show that Genifer substantially outperforms the previous state of the art for various settings on the CIFAR-100 and CUB-200 datasets.