在深度感知的固有歧义的范围内，现代相机的3D对象检测方法属于性能瓶颈。从直觉上讲，利用时间多视角立体声（MVS）技术是解决这种歧义的自然知识。但是，在适用于3D对象检测场景时，MV的传统尝试在两个方面存在缺陷：1）所有观点之间的亲和力测量遭受昂贵的计算成本； 2）很难处理经常移动物体的室外场景。为此，我们引入了一种有效的时间立体声方法，以动态选择匹配候选者的尺度，从而显着减少计算开销。更进一步，我们设计了一种迭代算法，以更新更有价值的候选人，使其适应移动候选人。我们将我们提出的方法实例化，以进行多视图3D检测器，即Bevstereo。 Bevstereo在Nuscenes数据集的仅相机轨道上实现了新的最先进的性能（即52.5％地图和61.0％NDS）。同时，广泛的实验反映了我们的方法比当代MVS方法更好地处理复杂的室外场景。代码已在https://github.com/megvii astection/bevstereo上发布。

学习准确的深度对于多视图3D对象检测至关重要。最近的方法主要是从单眼图像中学习深度，由于单眼深度学习的性质不足，这会面临固有的困难。在这项工作中，我们提出了一种新颖的环绕时间立体声（STS）技术，而不是使用唯一的单眼深度方法，而是利用跨时间之间的几何对应关系来促进准确的深度学习。具体而言，我们将自我车辆周围所有相机的视野视为统一的视图，即环绕浏览量，并在其上进行暂时立体声匹配。利用与STS不同框架之间的几何对应关系并与单眼深度结合在一起，以产生最终的深度预测。关于Nuscenes的综合实验表明，STS极大地提高了3D检测能力，特别是对于中距离和长距离对象。在带有RESNET-50骨架的BEVDEPTH上，STS分别提高了MAP和NDS，分别提高了2.6％和1.4％。当使用较大的主链和较大的图像分辨率时，观察到一致的改进，证明了其有效性

在这项研究中，我们提出了一个新的3D对象检测器，具有可信赖的深度估计，称为bevdepth，用于基于摄像机的鸟类视图（BEV）3D对象检测。通过对最近方法的彻底分析，我们发现没有摄像头信息的深度估计是隐式学习的，这使其成为创建以下伪点云的事实伪造深度。使用编码的内在和外在参数，BevDepth获得了明确的深度监督。进一步引入了深度校正子网络，以抵消深度地面真理中的投影引起的干扰。为了减少速度瓶颈，同时使用估计的深度将功能从图像视图投影到BEV中，还提出了快速的视频转换操作。此外，我们的bevdepth可以通过多帧的输入轻松扩展。 Bevdepth没有任何铃铛和哨子，可以在具有挑战性的Nuscenes测试套装上实现新的最新60.0％NDS，同时保持高效率。相机和激光雷达之间的性能差距首次在10％NDS之内大大降低。

Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.

如今，基于变压器的模型逐渐成为人工智能先驱的默认选择。即使在几个镜头的情况下，这些模型也会显示出优势。在本文中，我们重新审视了经典方法，并提出了一种新的几次替代方法。具体而言，我们研究了几个镜头的单级问题，该问题实际上以已知样本为参考来检测未知实例是否属于同一类。可以从序列匹配的角度研究此问题。结果表明，使用元学习，经典序列匹配方法，即比较聚集，显着优于变压器。经典方法所需的培训成本要少得多。此外，我们在简单的微调和元学习下进行两种序列匹配方法之间进行了经验比较。元学习导致变压器模型的特征具有高相关尺寸。原因与变压器模型的层和头数密切相关。实验代码和数据可从https://github.com/hmt2014/fewone获得

脆弱性识别对于软件相关行业的网络安全至关重要。早期识别方法需要在制作功能或注释脆弱的代码方面进行重大手动努力。尽管最近的预培训模型减轻了这个问题，但他们忽略了法规本身中包含的多个丰富结构信息。在本文中，我们提出了一种新型的多视图预训练模型（MV-PTM），该模型（MV-PTM）编码源代码的顺序和多类型结构信息，并使用对比度学习来增强代码表示。在两个公共数据集上进行的实验证明了MV-PTM的优势。特别是，就F1分数而言，MV-PTM平均将GraphCodebert提高了3.36 \％。

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.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.