When using LiDAR semantic segmentation models for safety-critical applications such as autonomous driving, it is essential to understand and improve their robustness with respect to a large range of LiDAR corruptions. In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions. To rigorously evaluate the robustness and generalizability of current approaches, we propose a new benchmark called SemanticKITTI-C, which features 16 out-of-domain LiDAR corruptions in three groups, namely adverse weather, measurement noise and cross-device discrepancy. Then, we systematically investigate 11 LiDAR semantic segmentation models, especially spanning different input representations (e.g., point clouds, voxels, projected images, and etc.), network architectures and training schemes. Through this study, we obtain two insights: 1) We find out that the input representation plays a crucial role in robustness. Specifically, under specific corruptions, different representations perform variously. 2) Although state-of-the-art methods on LiDAR semantic segmentation achieve promising results on clean data, they are less robust when dealing with noisy data. Finally, based on the above observations, we design a robust LiDAR segmentation model (RLSeg) which greatly boosts the robustness with simple but effective modifications. It is promising that our benchmark, comprehensive analysis, and observations can boost future research in robust LiDAR semantic segmentation for safety-critical applications.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, varying from mean output embedding to covariance and distributions. However, using embeddings in space lacks expressivity and cannot capture class information robustly, while statistical complex modeling poses difficulty to metric designs. In this work, we use tensor fields (``areas'') to model classes from the geometrical perspective for few-shot learning. We present a simple and effective method, dubbed hypersphere prototypes (HyperProto), where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere's center and the radius. Extending from points to areas, hyperspheres are much more expressive than embeddings. Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere. Following this idea, we also develop two variants of prototypes under other measurements. Extensive experiments and analysis on few-shot learning tasks across NLP and CV and comparison with 20+ competitive baselines demonstrate the effectiveness of our approach.

Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features, which has attracted considerable attention from both natural language processing and computer vision communities. Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases in the real world. In other words, the multilingual multimodal machine translation (Multilingual MMT) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for multiple languages. Besides, the image modality has no language boundaries, which is superior to bridging the semantic gap between languages. To this end, we first propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages. Then, an effective baseline LVP-M3 using visual prompts is proposed to support translations between different languages, which includes three stages (token encoding, language-aware visual prompt generation, and language translation). Extensive experimental results on our constructed benchmark datasets demonstrate the effectiveness of LVP-M3 method for Multilingual MMT.

由于其稀疏和细长的性质，估算3D空间中准确的车道线仍然具有挑战性。在这项工作中，我们提出了M^2-3dlanenet，这是一个有效3D车道检测的多模式框架。旨在集成来自多传感器的互补信息，M^2-3dlanenet首先将多模式特征提取具有模态特异性骨架，然后将它们融合在统一的鸟眼视图（BEV）空间中。具体而言，我们的方法由两个核心组成部分组成。 1）要获得准确的2D-3D映射，我们提出了自上而下的BEV生成。其中，使用线条限制的变形（LRDA）模块可用于以自上而下的方式有效地增强图像特征，从而充分捕获车道的细长特征。之后，它使用深度感知的举重将2D锥体特征投入到3D空间中，并通过枕形生成BEV特征。 2）我们进一步提出了自下而上的BEV融合，该融合通过多尺度的级联注意力汇总了多模式特征，从而集成了来自摄像头和激光雷达传感器的互补信息。足够的实验证明了M^2-3dlanenet的有效性，该实验的有效性超过了先前的最先进方法，即在OpenLane数据集上提高了12.1％的F1-SCORE改善。

由于缺乏异常样品，因此仅具有正常样本的先验知识的异常检测才吸引更多的注意力。现有的基于CNN的像素重建方法遇到了两个问题。首先，重建源和目标是包含无法区分的语义信息的原始像素值。其次，CNN倾向于很好地重建正常样品和异常情况，使它们仍然很难区分。在本文中，我们提出异常检测变压器（ADTR）将变压器应用于重建预训练的特征。预训练的功能包含可区分的语义信息。同样，采用变压器限制以很好地重构异常，因此一旦重建失败，就可以轻松检测到异常。此外，我们提出了新的损失函数，使我们的方法与正常样本的情况以及具有图像级和像素级标记为异常的异常情况兼容。通过添加简单的合成或外部无关异常，可以进一步提高性能。广泛的实验是在包括MVTEC-AD和CIFAR-10在内的异常检测数据集上进行的。与所有基线相比，我们的方法取得了卓越的性能。

基于激光雷达的3D单一对象跟踪是机器人技术和自动驾驶中的一个具有挑战性的问题。当前，现有方法通常会遇到长距离对象通常具有非常稀疏或部分倾斜的点云的问题，这使得模型含糊不清。模棱两可的功能将很难找到目标对象，并最终导致不良跟踪结果。为了解决此问题，我们使用功能强大的变压器体系结构，并为基于点云的3D单一对象跟踪任务提出一个点轨转换器（PTT）模块。具体而言，PTT模块通过计算注意力重量来生成微调的注意力特征，该功能指导追踪器的重点关注目标的重要功能，并提高复杂场景中的跟踪能力。为了评估我们的PTT模块，我们将PTT嵌入主要方法中，并构建一个名为PTT-NET的新型3D SOT跟踪器。在PTT-NET中，我们分别将PTT嵌入了投票阶段和提案生成阶段。投票阶段中的PTT模块可以模拟点斑块之间的交互作用，该点贴片学习上下文依赖于上下文。同时，提案生成阶段中的PTT模块可以捕获对象和背景之间的上下文信息。我们在Kitti和Nuscenes数据集上评估了PTT-NET。实验结果证明了PTT模块的有效性和PTT-NET的优越性，PTT-NET的优势超过了基线，在CAR类别中〜10％。同时，我们的方法在稀疏场景中也具有显着的性能提高。通常，变压器和跟踪管道的组合使我们的PTT-NET能够在两个数据集上实现最先进的性能。此外，PTT-NET可以在NVIDIA 1080TI GPU上实时以40fps实时运行。我们的代码是为研究社区开源的，网址为https://github.com/shanjiayao/ptt。

卷积神经网络（CNN）和变压器在多媒体应用中取得了巨大成功。但是，几乎没有努力有效，有效地协调这两个架构以满足图像的范围。本文旨在统一这两种架构，以利用其学习优点来降低图像。特别是，CNN的局部连通性和翻译等效性以及变压器中自我注意力（SA）的全球聚合能力被完全利用用于特定的局部环境和全球结构表示。基于雨水分布揭示降解位置和程度的观察，我们在帮助背景恢复之前引入退化，并因此呈现关联细化方案。提出了一种新型的多输入注意模块（MAM），以将降雨的去除和背景恢复关联。此外，我们为模型配备了有效的深度可分离卷积，以学习特定的特征表示并权衡计算复杂性。广泛的实验表明，我们提出的方法（称为ELF）的表现平均比最先进的方法（MPRNET）优于0.25 dB，但仅占其计算成本和参数的11.7 \％和42.1 \％。源代码可从https://github.com/kuijiang94/magic-elf获得。

我们提出了一个新的框架，以重建整体3D室内场景，包括单视图像的房间背景和室内对象。由于室内场景的严重阻塞，现有方法只能产生具有有限几何质量的室内物体的3D形状。为了解决这个问题，我们提出了一个与实例一致的隐式函数（InstPifu），以进行详细的对象重建。与实例对齐的注意模块结合使用，我们的方法有权将混合的局部特征与遮挡实例相结合。此外，与以前的方法不同，该方法仅代表房间背景为3D边界框，深度图或一组平面，我们通过隐式表示恢复了背景的精细几何形状。在E SUN RGB-D，PIX3D，3D-FUTURE和3D-FRONT数据集上进行的广泛实验表明，我们的方法在背景和前景对象重建中均优于现有方法。我们的代码和模型将公开可用。

利用在大规模图像文本对中预先训练的视觉和语言模型（VLM）成为开放式视觉识别的有希望的范式。在这项工作中，我们通过利用视频中自然存在的运动和音频来扩展这种范式。我们提出\ textbf {mov}，这是\ textbf {m} ult-imodal \ textbf {o} pen- \ textbf {v} ocabulary视频分类的简单而有效的方法。在MOV中，我们直接使用具有最小修改的预训练VLM的视觉编码器来编码视频，光流和音频频谱图。我们设计一种跨模式融合机制来汇总免费的多模式信息。 Kinetics-700和VGGSOUND的实验表明，引入流量或音频模态会带来预先训练的VLM和现有方法的大量性能增长。具体而言，MOV极大地提高了基础类别的准确性，而在新颖的课程上则更好地概括了。 MOV在UCF和HMDB零摄像视频分类基准上实现了最新结果，从而极大地超过了基于VLMS的传统零摄像方法和最新方法。代码和模型将发布。