In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series. DAMO-YOLO is extended from YOLO with some new technologies, including Neural Architecture Search (NAS), efficient Reparameterized Generalized-FPN (RepGFPN), a lightweight head with AlignedOTA label assignment, and distillation enhancement. In particular, we use MAE-NAS, a method guided by the principle of maximum entropy, to search our detection backbone under the constraints of low latency and high performance, producing ResNet-like / CSP-like structures with spatial pyramid pooling and focus modules. In the design of necks and heads, we follow the rule of "large neck, small head". We import Generalized-FPN with accelerated queen-fusion to build the detector neck and upgrade its CSPNet with efficient layer aggregation networks (ELAN) and reparameterization. Then we investigate how detector head size affects detection performance and find that a heavy neck with only one task projection layer would yield better results. In addition, AlignedOTA is proposed to solve the misalignment problem in label assignment. And a distillation schema is introduced to improve performance to a higher level. Based on these new techs, we build a suite of models at various scales to meet the needs of different scenarios, i.e., DAMO-YOLO-Tiny/Small/Medium. They can achieve 43.0/46.8/50.0 mAPs on COCO with the latency of 2.78/3.83/5.62 ms on T4 GPUs respectively. The code is available at https://github.com/tinyvision/damo-yolo.

现有的自动驾驶管道将感知模块与预测模块分开。这两个模块通过手工挑选的功能（例如代理框和轨迹）作为接口进行通信。由于这种分离，预测模块仅从感知模块接收部分信息。更糟糕的是，感知模块的错误会传播和积累，从而对预测结果产生不利影响。在这项工作中，我们提出了VIP3D，这是一种视觉轨迹预测管道，利用原始视频的丰富信息来预测场景中代理的未来轨迹。VIP3D在整个管道中采用稀疏的代理查询，使其完全可区分和可解释。此外，我们为这项新型的端到端视觉轨迹预测任务提出了评估度量。Nuscenes数据集的广泛实验结果表明，VIP3D在传统管道和以前的端到端模型上的强劲性能。

垂直联合学习（VFL）引起了很多关注，因为它可以以隐私的方式实现跨核数据合作。虽然大多数在VFL专注于线性和树模型的研究工作，但在VFL中尚未对深层模型（例如，神经网络）进行很好的研究。在本文中，我们专注于Splitnn，这是VFL中著名的神经网络框架，并确定了SplitNN中数据安全性和模型性能之间的权衡。简而言之，SplitNN通过交换梯度和转换数据来训练模型。一方面，SplitNN遭受了模型性能的损失，因为多方使用转换的数据而不是原始数据共同训练模型，并且丢弃了大量的低级特征信息。另一方面，通过在SplitNN中的较低层的汇总（即，数据的转换较小，保留了更低级别的功能）来提高模型性能的天真解决方案，使原始数据易受推理攻击的影响。为了减轻上述权衡，我们在VFL中提出了一个新的神经网络协议，称为安全远射聚合（SFA）。它改变了汇总转换数据并采用可移动掩码以保护原始数据的方式。实验结果表明，具有SFA的网络同时实现了数据安全性和高模型性能。

基于摄像头的3D对象探测器由于其更广泛的部署而欢迎其比LIDAR传感器较低。我们首先重新访问先前的立体声检测器DSGN，以表示代表3D几何和语义的立体音量构建方式。我们抛光立体声建模，并提出高级版本DSGN ++，旨在在三个主要方面增强整个2d到3D管道的有效信息流。首先，为了有效地将2D信息提高到立体声音量，我们提出了深度扫地（DPS），以允许较密集的连接并提取深度引导的特征。其次，为了掌握不同间距的功能，我们提出了一个新颖的立体声音量 - 双视立体声卷（DSV），该卷（DSV）集成了前视图和顶部视图功能，并重建了相机frustum中的子素深度。第三，随着前景区域在3D空间中的占主导地位，我们提出了一种多模式数据编辑策略-Stereo-lidar拷贝性 - 可确保跨模式对齐并提高数据效率。没有铃铛和哨子，在流行的Kitti基准测试中的各种模式设置中进行了广泛的实验表明，我们的方法始终优于所有类别的基于相机的3D检测器。代码可从https://github.com/chenyilun95/dsgn2获得。

开放程序代表全球手术的主要形式。人工智能（AI）有可能优化手术实践并改善患者结果，但努力主要集中在微创技术上。我们的工作通过策划，从YouTube，从YouTube，Open Surgical视频的最大数据集克服了培训AI模型的现有数据限制：1997年从50个国家上传的23个外科手术的视频。使用此数据集，我们开发了一种能够实时了解外科行为，手和工具的多任务AI模型 - 程序流程和外科医生技能的构建块。我们表明我们的模型推广了各种外科类型和环境。说明这种普遍性，我们直接应用了YouTube培训的模型，分析了在学术医疗中心前瞻性收集的开放式手术，并确定了与手动效率相关的外科技能的运动学描述符。我们的开放外科（AVOS）数据集和培训模式的注释视频将可用于进一步发展外科艾。

由于可能的颜色失真和输入图像的最亮和最黑暗的区域中可能的颜色失真和丢失丢失，缝合不同曝光的多个图像充满挑战。本文首先通过引入加权直方图平均（WHA）的新概念来提出一种新型颜色映射算法。所提出的WHA算法利用通过使用颜色映射函数（CMFS）的非降低性能而建立的两个图像的直方图间距之间的对应关系。然后采用WHA算法来合成一组不同暴露的全景图像。中间全景图像最终通过最先进的多尺度曝光融合（MEF）算法融合以产生最终的全景图像。广泛的实验表明，所提出的WHA算法显着超越了相关最新的彩色映射方法。基于MEF的提出的高动态范围（HDR）拼接算法也在输入图像的最亮和最黑暗的区域中保留细节。相关材料将在https://github.com/yilun-xu/wha公开访问可重复的研究。

空间变化暴露（SVE）是高动态（HDR）成像（HDRI）的有希望的选择。被称为单射HDRI的SVE的HDRI是一种有效的解决方案，以避免重影文物。然而，恢复从真实世界的图像与SVE恢复全分辨率的HDR图像是非常具有挑战性的，因为：a）在拜耳图案中，通过相机捕获具有不同曝光的三分之一的像素，B）捕获的一些捕获像素过于和暴露。对于以前的挑战，设计了一种空间变化的卷积（SVC）来设计以改变曝光的携带携带的拜耳图像。对于后者，提出了一种曝光 - 引导方法，以防止来自暴露和暴露的像素的干扰。最后，联合去脱模和HDRI深度学习框架被形式化以包括两种新型组件，并实现端到端的单次HDRI。实验表明，所提出的端到端框架避免了累积误差问题并超越了相关的最先进的方法。

The topic of multi-person pose estimation has been largely improved recently, especially with the development of convolutional neural network. However, there still exist a lot of challenging cases, such as occluded keypoints, invisible keypoints and complex background, which cannot be well addressed. In this paper, we present a novel network structure called Cascaded Pyramid Network (CPN) which targets to relieve the problem from these "hard" keypoints. More specifically, our algorithm includes two stages: Glob-alNet and RefineNet. GlobalNet is a feature pyramid network which can successfully localize the "simple" keypoints like eyes and hands but may fail to precisely recognize the occluded or invisible keypoints. Our RefineNet tries explicitly handling the "hard" keypoints by integrating all levels of feature representations from the Global-Net together with an online hard keypoint mining loss. In general, to address the multi-person pose estimation problem, a top-down pipeline is adopted to first generate a set of human bounding boxes based on a detector, followed by our CPN for keypoint localization in each human bounding box. Based on the proposed algorithm, we achieve stateof-art results on the COCO keypoint benchmark, with average precision at 73.0 on the COCO test-dev dataset and 72.1 on the COCO test-challenge dataset, which is a 19% relative improvement compared with 60.5 from the COCO 2016 keypoint challenge. Code 1 and the detection results are publicly available for further research.

Human evaluation is the foundation upon which the evaluation of both summarization systems and automatic metrics rests. However, existing human evaluation protocols and benchmarks for summarization either exhibit low inter-annotator agreement or lack the scale needed to draw statistically significant conclusions, and an in-depth analysis of human evaluation is lacking. In this work, we address the shortcomings of existing summarization evaluation along the following axes: 1) We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which relies on fine-grained semantic units and allows for high inter-annotator agreement. 2) We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of over 22k summary-level annotations over state-of-the-art systems on three datasets. 3) We compare our ACU protocol with three other human evaluation protocols, underscoring potential confounding factors in evaluation setups. 4) We evaluate existing automatic metrics using the collected human annotations across evaluation protocols and demonstrate how our benchmark leads to more statistically stable and significant results. Furthermore, our findings have important implications for evaluating large language models (LLMs), as we show that LLMs adjusted by human feedback (e.g., GPT-3.5) may overfit unconstrained human evaluation, which is affected by the annotators' prior, input-agnostic preferences, calling for more robust, targeted evaluation methods.

Humans form mental images of 3D scenes to support counterfactual imagination, planning, and motor control. Our abilities to predict the appearance and affordance of the scene from previously unobserved viewpoints aid us in performing manipulation tasks (e.g., 6-DoF kitting) with a level of ease that is currently out of reach for existing robot learning frameworks. In this work, we aim to build artificial systems that can analogously plan actions on top of imagined images. To this end, we introduce Mental Imagery for Robotic Affordances (MIRA), an action reasoning framework that optimizes actions with novel-view synthesis and affordance prediction in the loop. Given a set of 2D RGB images, MIRA builds a consistent 3D scene representation, through which we synthesize novel orthographic views amenable to pixel-wise affordances prediction for action optimization. We illustrate how this optimization process enables us to generalize to unseen out-of-plane rotations for 6-DoF robotic manipulation tasks given a limited number of demonstrations, paving the way toward machines that autonomously learn to understand the world around them for planning actions.