This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments. In this paper, we treat the MOT task as a two-stage task including human detection and trajectory matching. Specifically, we designed an improved human detector and associated most of detection to guarantee the integrity of the motion trajectory. We also propose a location-wise matching matrix to obtain more accurate trace matching. Without any model merging, our method achieves 66.672 HOTA and 93.971 MOTA on the DanceTrack challenge dataset.

It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a sentence sequentially and equally. In this paper, we propose an uncertainty-aware image captioning framework, which parallelly and iteratively operates insertion of discontinuous candidate words between existing words from easy to difficult until converged. We hypothesize that high-uncertainty words in a sentence need more prior information to make a correct decision and should be produced at a later stage. The resulting non-autoregressive hierarchy makes the caption generation explainable and intuitive. Specifically, we utilize an image-conditioned bag-of-word model to measure the word uncertainty and apply a dynamic programming algorithm to construct the training pairs. During inference, we devise an uncertainty-adaptive parallel beam search technique that yields an empirically logarithmic time complexity. Extensive experiments on the MS COCO benchmark reveal that our approach outperforms the strong baseline and related methods on both captioning quality as well as decoding speed.

For saving cost, many deep neural networks (DNNs) are trained on third-party datasets downloaded from internet, which enables attacker to implant backdoor into DNNs. In 2D domain, inherent structures of different image formats are similar. Hence, backdoor attack designed for one image format will suite for others. However, when it comes to 3D world, there is a huge disparity among different 3D data structures. As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene. Therefore, this paper designs a uniform backdoor pattern: NRBdoor (Noisy Rotation Backdoor) which is able to adapt for heterogeneous 3D data structures. Specifically, we start from the unit rotation and then search for the optimal pattern by noise generation and selection process. The proposed NRBdoor is natural and imperceptible, since rotation is a common operation which usually contains noise due to both the miss match between a pair of points and the sensor calibration error for real-world 3D scene. Extensive experiments on 3D mesh and point cloud show that the proposed NRBdoor achieves state-of-the-art performance, with negligible shape variation.

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone on the ADE20K dataset and achieves new state-of-the-art performance on COCO-Stuff-10K and PASCAL-Context datasets. Furthermore, to reduce the computational cost of the ViT backbone, we propose query-based down-sampling (QD) and query-based up-sampling (QU) to build a Shrunk structure. With the proposed Shrunk structure, the model can save up to $40\%$ computations while maintaining competitive performance.

Recently, vector quantized autoregressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space. Although the simple generative process surprisingly works well, is this the best way to generate the image? For instance, human creation is more inclined to the outline-to-fine of an image, while VQ-AR models themselves do not consider any relative importance of each component. In this paper, we present a progressive denoising model for high-fidelity text-to-image image generation. The proposed method takes effect by creating new image tokens from coarse to fine based on the existing context in a parallel manner and this procedure is recursively applied until an image sequence is completed. The resulting coarse-to-fine hierarchy makes the image generation process intuitive and interpretable. Extensive experiments demonstrate that the progressive model produces significantly better results when compared with the previous VQ-AR method in FID score across a wide variety of categories and aspects. Moreover, the text-to-image generation time of traditional AR increases linearly with the output image resolution and hence is quite time-consuming even for normal-size images. In contrast, our approach allows achieving a better trade-off between generation quality and speed.

大多数现有的语义分割方法都以图像级类标签作为监督，高度依赖于从标准分类网络生成的初始类激活图（CAM）。在本文中，提出了一种新颖的“渐进贴片学习”方法，以改善分类的局部细节提取，从而更好地覆盖整个对象的凸轮，而不仅仅是在常规分类模型中获得的CAM中的最歧视区域。 “补丁学习”将特征映射破坏成贴片，并在最终聚合之前并行独立处理每个本地贴片。这样的机制强迫网络从分散的歧视性本地部分中找到弱信息，从而提高了本地细节的敏感性。 “渐进的补丁学习”进一步将特征破坏和补丁学习扩展到多层粒度。与多阶段优化策略合作，这种“渐进的补丁学习”机制隐式地为模型提供了跨不同位置粒状性的特征提取能力。作为隐式多粒性渐进式融合方法的替代方案，我们还提出了一种明确的方法，以同时将单个模型中不同粒度的特征融合，从而进一步增强了完整对象覆盖的凸轮质量。我们提出的方法在Pascal VOC 2012数据集上取得了出色的性能，例如，测试集中有69.6 $％miou），它超过了大多数现有的弱监督语义细分方法。代码将在此处公开提供，https://github.com/tyroneli/ppl_wsss。

生成精确的类感知的伪基真实，也就是类激活图（CAM），对于弱监督的语义分割至关重要。原始CAM方法通常会产生不完整和不准确的定位图。为了解决这个问题，本文提出了基于可变形卷积中的偏移学习的扩展和收缩方案，以依次改善两个各个阶段中定位对象的回忆和精度。在扩展阶段，在可变形卷积层中的偏移学习分支，称为“扩展采样器”，寻求采样越来越小的判别对象区域，这是由逆监督信号驱动的，从而最大程度地提高了图像级分类损失。然后在收缩阶段逐渐将位置更完整的物体逐渐缩小到最终对象区域。在收缩阶段，引入了另一个可变形卷积层的偏移学习分支，称为“收缩采样器”，以排除在扩展阶段参加的假积极背景区域，以提高定位图的精度。我们在Pascal VOC 2012和MS Coco 2014上进行了各种实验，以很好地证明了我们方法比其他最先进的方法对弱监督语义分割的优越性。代码将在此处公开提供，https://github.com/tyroneli/esol_wsss。

融合激光雷达和相机信息对于在自动驾驶系统中实现准确可靠的3D对象检测至关重要。但是，由于难以结合两个截然不同的方式的多晶格几何和语义特征，因此这是具有挑战性的。最近的方法旨在通过2D摄像机图像中的提升点（称为种子）中的3D空间来探索相机功能的语义密度，并且可以将它们大致分为1）1）原始点的早期融合，旨在增强3D在早期输入阶段的点云，以及2）Bev（鸟眼视图）的后期融合，在检测头之前合并了LiDar和Camera BEV功能。尽管两者在增强联合特征的表示能力方面都具有优点，但这种单级融合策略是对上述挑战的次优点。他们的主要缺点是无法充分从两种不同的方式中相互作用的多晶格语义特征。为此，我们提出了一个新颖的框架，该框架着重于多粒性激光雷达和相机功能的多尺度渐进互动。我们提出的方法缩写为MDMSFusion，实现最先进的方法可导致3D对象检测，在Nuscenes验证集上具有69.1 MAP和71.8 NDS，在NUSCENES测试集上进行了70.8 MAP和73.2 nds，该级别的第一和第二级和第二个NDS。在提交时，在单模型的非集结方法中。

多年来，Yolo系列一直是有效对象检测的事实上的行业级别标准。尤洛社区（Yolo Community）绝大多数繁荣，以丰富其在众多硬件平台和丰富场景中的使用。在这份技术报告中，我们努力将其限制推向新的水平，以坚定不移的行业应用心态前进。考虑到对真实环境中速度和准确性的多种要求，我们广泛研究了行业或学术界的最新对象检测进步。具体而言，我们从最近的网络设计，培训策略，测试技术，量化和优化方法中大量吸收了思想。最重要的是，我们整合了思想和实践，以在各种规模上建立一套可供部署的网络，以适应多元化的用例。在Yolo作者的慷慨许可下，我们将其命名为Yolov6。我们还向用户和贡献者表示热烈欢迎，以进一步增强。为了了解性能，我们的Yolov6-N在NVIDIA TESLA T4 GPU上以1234 fps的吞吐量在可可数据集上击中35.9％的AP。 Yolov6-S在495 fps处的43.5％AP罢工，在相同规模〜（Yolov5-S，Yolox-S和Ppyoloe-S）上超过其他主流探测器。我们的量化版本的Yolov6-S甚至在869 fps中带来了新的43.3％AP。此外，与其他推理速度相似的检测器相比，Yolov6-m/L的精度性能（即49.5％/52.3％）更好。我们仔细进行了实验以验证每个组件的有效性。我们的代码可在https://github.com/meituan/yolov6上提供。

Panoptic叙事接地（PNG）是一项新的任务，其目标是通过静止图像的密集叙事标题来分割事物和内容类别的视觉对象。先前的两阶段方法首先提取了通过现成的全盘分割模型提取分割区域的建议，然后进行粗糙的区域短语匹配，以将每个名词短语的候选区域接地。但是，两阶段的管道通常受到第一阶段低质量建议的性能限制，以及由区域特征池的损失以及为事物和东西类别设计的复杂策略引起的空间细节。为了减轻这些缺点，我们提出了一个单阶段的端到端像素匹配网络（PPMN），该网络将每个短语与其相应的像素直接匹配，而不是区域建议，并通过简单组合输出全段段。因此，我们的模型可以从密集注释的像素色素对的监督而不是稀疏的区域短语对中利用足够，更精细的跨模式语义对应关系。此外，我们还提出了与语言兼容的像素聚合（LCPA）模块，以进一步通过多轮修补剂增强短语特征的判别能力，该简化为每个短语选择最兼容的像素以适应相应的视觉上下文。广泛的实验表明，我们的方法在PNG基准测试中实现了新的最新性能，并具有4.0个绝对平均召回率增长。