As Deep Neural Networks (DNNs) are increasingly deployed in safety critical and privacy sensitive applications such as autonomous driving and biometric authentication, it is critical to understand the fault-tolerance nature of DNNs. Prior work primarily focuses on metrics such as Failures In Time (FIT) rate and the Silent Data Corruption (SDC) rate, which quantify how often a device fails. Instead, this paper focuses on quantifying the DNN accuracy given that a transient error has occurred, which tells us how well a network behaves when a transient error occurs. We call this metric Resiliency Accuracy (RA). We show that existing RA formulation is fundamentally inaccurate, because it incorrectly assumes that software variables (model weights/activations) have equal faulty probability under hardware transient faults. We present an algorithm that captures the faulty probabilities of DNN variables under transient faults and, thus, provides correct RA estimations validated by hardware. To accelerate RA estimation, we reformulate RA calculation as a Monte Carlo integration problem, and solve it using importance sampling driven by DNN specific heuristics. Using our lightweight RA estimation method, we show that transient faults lead to far greater accuracy degradation than what todays DNN resiliency tools estimate. We show how our RA estimation tool can help design more resilient DNNs by integrating it with a Network Architecture Search framework.

目前，深度神经网络（DNN）在不同的应用中被广泛采用。尽管具有商业价值，但培训良好的DNN仍在资源消费。因此，训练有素的模型是其所有者的宝贵知识产权。但是，最近的研究揭示了模型窃取的威胁，即使他们只能查询模型，对手也可以获得受害者模型的功能相似的副本。在本文中，我们提出了一个有效且无害的模型所有权验证（移动），以防御不同类型的模型窃取，而无需引入新的安全风险。通常，我们通过验证可疑模型是否包含辩护人指定的外部特征的知识来进行所有权验证。具体而言，我们通过将一些训练样本带来样式转移来嵌入外部功能。然后，我们训练一个元分类器，以确定模型是否被受害者偷走了。这种方法的灵感来自于理解，即被盗模型应包含受害者模型学到的功能的知识。特别是，我们在白色框和黑框设置下开发了移动方法，以提供全面的模型保护。基准数据集的广泛实验验证了我们方法的有效性及其对潜在适应性攻击的抵抗力。复制我们方法的主要实验的代码可在\ url {https://github.com/thuyimingli/move}上获得。

最近，类似于MLP的视觉模型已在主流视觉识别任务上实现了有希望的表演。与视觉变压器和CNN相反，类似MLP的模型的成功表明，令牌和渠道之间的简单信息融合操作可以为深度识别模型带来良好的表示能力。但是，现有的类似于MLP的模型通过静态融合操作融合代币，缺乏对代币内容的适应性。因此，习惯信息融合程序不够有效。为此，本文介绍了一种有效的MLP式网络体系结构，称为Dynamixer，诉诸动态信息融合。至关重要的是，我们提出了一个程序，该过程依赖于该过程，以通过利用混合所有令牌的内容来动态生成混合矩阵。为了减少时间复杂性并提高鲁棒性，采用了降低性降低技术和多段融合机制。我们提出的Dynamixer模型（9700万参数）在没有额外的训练数据的情况下，在Imagenet-1k数据集上实现了84.3 \％TOP-1的精度，对最先进的视觉MLP模型表现出色。当参数数量减少到26m时，它仍然可以达到82.7 \％TOP-1的精度，超过了具有相似容量的现有MLP样模型。该代码可在\ url {https://github.com/ziyuwwang/dynamixer}中获得。

获得训练有素的模型涉及昂贵的数据收集和培训程序，因此该模型是有价值的知识产权。最近的研究表明，即使在没有培训样本，也可以“窃取”部署模型，无法访问模型参数或结构。目前，有一些防御方法可以减轻这种威胁，主要是提高模型窃取的成本。在本文中，我们通过验证可疑模型是否包含对Defender指定的知识{外部特征}来探讨其他角度的防御。具体而言，我们通过用风格的转移回火，嵌入外部特征。然后，我们培训一个元分类器以确定模型是否从受害者中偷走。这种方法是通过了解偷窃模型应该包含受害者模型学习的特征知识的启发。我们在Cifar-10和Imagenet数据集中检查我们的方法。实验结果表明，即使通过多级窃取过程获得被盗模型，我们的方法在同时检测不同类型的模型窃取。再现主要结果的代码可在Github（https://github.com/zlh-thu/stealing验证）上获得。

Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. However, in practice, PCDs are often incomplete when objects are viewed from few and sparse viewpoints before the grasping action, leading to the generation of wrong or inaccurate grasp poses. We propose a novel grasping strategy, named 3DSGrasp, that predicts the missing geometry from the partial PCD to produce reliable grasp poses. Our proposed PCD completion network is a Transformer-based encoder-decoder network with an Offset-Attention layer. Our network is inherently invariant to the object pose and point's permutation, which generates PCDs that are geometrically consistent and completed properly. Experiments on a wide range of partial PCD show that 3DSGrasp outperforms the best state-of-the-art method on PCD completion tasks and largely improves the grasping success rate in real-world scenarios. The code and dataset will be made available upon acceptance.

Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence and video segments on a single temporal resolution, while neglecting the temporal consistency of video content in different resolutions. In this work, we propose a novel multi-resolution temporal video sentence grounding network: MRTNet, which consists of a multi-modal feature encoder, a Multi-Resolution Temporal (MRT) module, and a predictor module. MRT module is an encoder-decoder network, and output features in the decoder part are in conjunction with Transformers to predict the final start and end timestamps. Particularly, our MRT module is hot-pluggable, which means it can be seamlessly incorporated into any anchor-free models. Besides, we utilize a hybrid loss to supervise cross-modal features in MRT module for more accurate grounding in three scales: frame-level, clip-level and sequence-level. Extensive experiments on three prevalent datasets have shown the effectiveness of MRTNet.

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. \mr{Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency.} \mr{As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation.} To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve \mr{diverse types of high-level and low-level} downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors. We will make the code and data publicly available at https://github.com/keeganhk/Flattening-Net.

We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks. We compare the performance of the LM method with other popular first-order algorithms such as SGD and Adam, as well as other second-order algorithms such as L-BFGS , Hessian-Free and KFAC. We further speed up the LM method by using adaptive momentum, learning rate line search, and uphill step acceptance.

Pre-trained language models achieve superior performance, but they are computationally expensive due to their large size. Techniques such as pruning and knowledge distillation (KD) have been developed to reduce their size and latency. In most structural pruning methods, the pruning units, such as attention heads and feed-forward hidden dimensions, only span a small model structure space and limit the structures that the pruning algorithm can explore. In this work, we propose Gradient-based Intra-attention pruning (GRAIN), which inspects fine intra-attention structures, and allows different heads to have different sizes. Intra-attention pruning greatly expands the searching space of model structures and yields highly heterogeneous structures. We further propose structure regularization to encourage generating more regular structures, which achieves higher speedups than heterogeneous ones. We also integrate KD into the pruning process with a gradient separation strategy to reduce the interference of KD with the pruning process. GRAIN is evaluated on a variety of tasks. Results show that it notably outperforms other methods at the same or similar model size. Even under extreme compression where only $3\%$ weights in transformers remain, the pruned model is still competitive.

Aiming at highly accurate object detection for connected and automated vehicles (CAVs), this paper presents a Deep Neural Network based 3D object detection model that leverages a three-stage feature extractor by developing a novel LIDAR-Camera fusion scheme. The proposed feature extractor extracts high-level features from two input sensory modalities and recovers the important features discarded during the convolutional process. The novel fusion scheme effectively fuses features across sensory modalities and convolutional layers to find the best representative global features. The fused features are shared by a two-stage network: the region proposal network (RPN) and the detection head (DH). The RPN generates high-recall proposals, and the DH produces final detection results. The experimental results show the proposed model outperforms more recent research on the KITTI 2D and 3D detection benchmark, particularly for distant and highly occluded instances.