In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training techniques, the resulting object detector, named RTMDet, achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, outperforming the current mainstream industrial detectors. RTMDet achieves the best parameter-accuracy trade-off with tiny/small/medium/large/extra-large model sizes for various application scenarios, and obtains new state-of-the-art performance on real-time instance segmentation and rotated object detection. We hope the experimental results can provide new insights into designing versatile real-time object detectors for many object recognition tasks. Code and models are released at https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet.

在此技术报告中，我们提出了我们的解决方案，称为MV-FCOS3D ++，适用于Waymo Open DataSet Challenge的仅摄像头3D检测轨道2022.仅使用birde-eye-view或3D检测多视图摄像头3D检测几何表示可以利用相邻视图之间重叠区域的立体声提示，而无需手工制作的后处理即可直接执行3D检测。但是，它缺乏对2D骨架的直接语义监督，可以通过预处理简单的单眼探测器来补充。我们的解决方案是此范式之后用于4D检测的多视图框架。它是基于简单的单眼检测器FCOS3D ++构建的，仅通过Waymo的对象注释进行了预定，并将多视图功能转换为3D网格空间以检测其上的3D对象。设计了单帧理解和时间立体声匹配的双路径颈部，以结合多帧信息。我们的方法最终通过单个模型实现了49.75％的MAPL，并在WOD挑战中赢得了第二名，而在训练过程中没有任何基于激光雷达的深度监督。该代码将在https://github.com/tai-wang/depth-from-motion上发布。

我们提出了一个名为mmrotate的开源工具箱，该工具箱提供了基于深度学习的流行旋转对象检测算法的训练，推断和评估的连贯算法框架。mmrotate实现了18种最先进的算法，并支持三种最常用的角度定义方法。为了促进与旋转对象检测有关的问题的未来研究和工业应用，我们还提供了大量训练有素的模型和详细的基准测试，以深入了解旋转对象检测的性能。mmrotate将于https://github.com/open-mmlab/mmrotate公开发布。

本文介绍了密集的暹罗网络（Denseiam），这是一个简单的无监督学习框架，用于密集的预测任务。它通过以两种类型的一致性（即像素一致性和区域一致性）之间最大化一个图像的两个视图之间的相似性来学习视觉表示。具体地，根据重叠区域中的确切位置对应关系，Denseiam首先最大化像素级的空间一致性。它还提取一批与重叠区域中某些子区域相对应的区域嵌入，以形成区域一致性。与以前需要负像素对，动量编码器或启发式面膜的方法相反，Denseiam受益于简单的暹罗网络，并优化了不同粒度的一致性。它还证明了简单的位置对应关系和相互作用的区域嵌入足以学习相似性。我们将Denseiam应用于ImageNet，并在各种下游任务上获得竞争性改进。我们还表明，只有在一些特定于任务的损失中，简单的框架才能直接执行密集的预测任务。在现有的无监督语义细分基准中，它以2.1 miou的速度超过了最新的细分方法，培训成本为28％。代码和型号在https://github.com/zwwwayne/densesiam上发布。

尽管有不同的相关框架，已经通过不同和专门的框架解决了语义，实例和Panoptic分段。本文为这些基本相似的任务提供了统一，简单，有效的框架。该框架，名为K-Net，段段由一组被学习内核持续一致，其中每个内核负责为潜在实例或填充类生成掩码。要解决区分各种实例的困难，我们提出了一个内核更新策略，使每个内核动态和条件在输入图像中的有意义的组上。 K-NET可以以结尾的方式培训，具有二分匹配，其培训和推论是自然的NMS和无框。没有钟声和口哨，K-Net超越了先前发表的全面的全面的单一模型，在ADE20K Val上的MS Coco Test-Dev分割和语义分割上分别与55.2％PQ和54.3％Miou分裂。其实例分割性能也与MS COCO上的级联掩模R-CNN相同，具有60％-90％的推理速度。代码和模型将在https://github.com/zwwwayne/k-net/发布。

The key to electroencephalography (EEG)-based brain-computer interface (BCI) lies in neural decoding, and its accuracy can be improved by using hybrid BCI paradigms, that is, fusing multiple paradigms. However, hybrid BCIs usually require separate processing processes for EEG signals in each paradigm, which greatly reduces the efficiency of EEG feature extraction and the generalizability of the model. Here, we propose a two-stream convolutional neural network (TSCNN) based hybrid brain-computer interface. It combines steady-state visual evoked potential (SSVEP) and motor imagery (MI) paradigms. TSCNN automatically learns to extract EEG features in the two paradigms in the training process, and improves the decoding accuracy by 25.4% compared with the MI mode, and 2.6% compared with SSVEP mode in the test data. Moreover, the versatility of TSCNN is verified as it provides considerable performance in both single-mode (70.2% for MI, 93.0% for SSVEP) and hybrid-mode scenarios (95.6% for MI-SSVEP hybrid). Our work will facilitate the real-world applications of EEG-based BCI systems.

在保持最佳控制性能的同时，减少传感器要求对于许多工业控制应用至关重要，以实现强大的，低成本和计算有效的控制器。但是，对于典型的机器学习域的现有特征选择解决方案几乎不可能通过变化的动态来控制在控制域中。在本文中，一个新颖的框架，即双世界嵌入式细心特征选择（D-AFS），可以有效地为动态控制下的系统选择最相关的传感器。 D-AFS并没有在大多数深度强化学习（DRL）算法中使用的一个世界，而是具有扭曲功能的现实世界和虚拟同行。通过分析在两个世界中DRL的响应，D-AFS可以定量确定各自特征对控制的重要性。众所周知的主动流控制问题，圆柱阻力减少，用于评估。结果表明，D-AFS成功地发现了比最先进的解决方案，比人类专家的五探针布局比最先进的解决方案进行了18.7 \％阻力的优化五探针布局。我们还将该解决方案应用于四个OpenAI经典控制案例。在所有情况下，D-AFS都比最初提供的解决方案获得相同或更好的传感器配置。我们认为，结果突出显示了为实验或工业系统实现高效和最佳传感器设计的一种新方法。我们的源代码可在https://github.com/g-yab/dafsfluid上公开提供。

日志是确保许多软件系统的可靠性和连续性，尤其是大规模分布式系统的命令。他们忠实地录制运行时信息，以便于系统故障排除和行为理解。由于现代软件系统的大规模和复杂性，日志量已达到前所未有的水平。因此，对于基于逻究的异常检测，常规的手动检查方法甚至传统的基于机器学习的方法变得不切实际，这是一种不切实际的是，作为基于深度学习的解决方案的快速发展的催化剂。然而，目前在诉诸神经网络的代表性日志的异常探测器之间缺乏严格的比较。此外，重新实现过程需要不琐碎的努力，并且可以轻易引入偏差。为了更好地了解不同异常探测器的特性，在本文中，我们提供了六种最先进的方法使用的五种流行神经网络的全面审查和评估。特别是，4种所选方法是无监督的，并且剩下的两个是监督的。这些方法是用两个公开的日志数据集进行评估，其中包含近1600万日志消息和总共有04万个异常实例。我们相信我们的工作可以作为这一领域的基础，为未来的学术研究和工业应用做出贡献。

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.