In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth estimation. Nevertheless, the latency of vision-centric approaches is too high for practical deployment (e.g., most camera-based 3D detectors have a runtime greater than 300ms). To bridge the gap between ideal research and real-world applications, it is necessary to quantify the trade-off between performance and efficiency. Traditionally, autonomous-driving perception benchmarks perform the offline evaluation, neglecting the inference time delay. To mitigate the problem, we propose the Autonomous-driving StreAming Perception (ASAP) benchmark, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving. On the basis of the 2Hz annotated nuScenes dataset, we first propose an annotation-extending pipeline to generate high-frame-rate labels for the 12Hz raw images. Referring to the practical deployment, the Streaming Perception Under constRained-computation (SPUR) evaluation protocol is further constructed, where the 12Hz inputs are utilized for streaming evaluation under the constraints of different computational resources. In the ASAP benchmark, comprehensive experiment results reveal that the model rank alters under different constraints, suggesting that the model latency and computation budget should be considered as design choices to optimize the practical deployment. To facilitate further research, we establish baselines for camera-based streaming 3D detection, which consistently enhance the streaming performance across various hardware. ASAP project page: https://github.com/JeffWang987/ASAP.
translated by 谷歌翻译
In this paper, we present a simple yet surprisingly effective technique to induce "selective amnesia" on a backdoored model. Our approach, called SEAM, has been inspired by the problem of catastrophic forgetting (CF), a long standing issue in continual learning. Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data. We analyzed SEAM by modeling the unlearning process as continual learning and further approximating a DNN using Neural Tangent Kernel for measuring CF. Our analysis shows that our random-labeling approach actually maximizes the CF on an unknown backdoor in the absence of triggered inputs, and also preserves some feature extraction in the network to enable a fast revival of the primary task. We further evaluated SEAM on both image processing and Natural Language Processing tasks, under both data contamination and training manipulation attacks, over thousands of models either trained on popular image datasets or provided by the TrojAI competition. Our experiments show that SEAM vastly outperforms the state-of-the-art unlearning techniques, achieving a high Fidelity (measuring the gap between the accuracy of the primary task and that of the backdoor) within a few minutes (about 30 times faster than training a model from scratch using the MNIST dataset), with only a small amount of clean data (0.1% of training data for TrojAI models).
translated by 谷歌翻译
Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.
translated by 谷歌翻译
域的概括旨在学习一个可以很好地概括在看不见的测试数据集(即分布数据集)上的模型,该数据与培训数据集不同。为了解决计算机视觉中的领域概括,我们将损失景观理论引入该领域。具体而言,我们从损失景观的角度从四个方面(包括骨干,正则化,训练范式和学习率)引起了深度学习模型的概括能力。我们通过进行广泛的消融研究和可视化来验证有关NICO ++,PAC和VLCS数据集的提议理论。此外,我们将该理论应用于ECCV 2022 NICO挑战1,并在不使用任何域不变方法的情况下获得第三名。
translated by 谷歌翻译
现有的远处监督的关系提取器通常依靠嘈杂的数据进行模型培训和评估,这可能导致垃圾堆放系统。为了减轻问题,我们研究了小型清洁数据集是否可以帮助提高远距离监督模型的质量。我们表明,除了对模型进行更具说服力的评估外,一个小的清洁数据集还可以帮助我们构建更强大的Denoising模型。具体而言,我们提出了一个基于影响函数的清洁实例选择的新标准。它收集了样本级别的证据,以识别良好实例(这比损失级别的证据更具信息性)。我们还提出了一种教师实习机制,以控制自举套件时中间结果的纯度。整个方法是模型不合时宜的,并且在denoising Real(NYT)和合成噪声数据集上都表现出强烈的性能。
translated by 谷歌翻译
神经文本排名模型已经见证了显着的进步,并越来越多地在实践中部署。不幸的是,它们还继承了一般神经模型的对抗性脆弱性,这些神经模型已被检测到,但仍未被先前的研究所忽视。此外,Blackhat SEO可能会利用继承的对抗性漏洞来击败受保护的搜索引擎。在这项研究中,我们提出了对黑盒神经通道排名模型的模仿对抗攻击。我们首先表明,可以通过列举关键查询/候选者,然后训练排名模仿模型来透明和模仿目标段落排名模型。利用排名模仿模型,我们可以精心操纵排名结果并将操纵攻击转移到目标排名模型。为此,我们提出了一种由成对目标函数授权的基于创新的基于梯度的攻击方法,以产生对抗性触发器,该触发器会导致有预谋的混乱,而具有很少的令牌。为了配备触发器的伪装,我们将下一个句子预测损失和语言模型流利度限制添加到目标函数中。对通过排名的实验结果证明了对各种SOTA神经排名模型的排名模仿攻击模型和对抗触发器的有效性。此外,各种缓解分析和人类评估表明,在面对潜在的缓解方法时,伪装的有效性。为了激励其他学者进一步研究这一新颖和重要的问题,我们将实验数据和代码公开可用。
translated by 谷歌翻译
图像引导放射疗法中的CBCT为患者的设置和计划评估提供了关键的解剖学信息。纵向CBCT图像登记可以量化分裂间的解剖变化。这项研究的目的是提出一个无监督的基于深度学习的CBCT-CBCT变形图像登记。提出的可变形注册工作流程包括训练和推理阶段,这些培训和推理阶段通过基于空间转换的网络(STN)共享相同的进率前路。 STN由全球生成对抗网络(Globalgan)和本地GAN(Localgan)组成,分别预测了粗略和细尺度运动。通过最小化图像相似性损失和可变形矢量场(DVF)正则化损失,而无需监督地面真实DVF的训练,对网络进行了训练。在推理阶段,训练有素的Localgan预测了局部DVF的斑块,并融合形成全图像DVF。随后将局部全图像DVF与Globalgan生成的DVF合并以获得最终的DVF。在实验中,使用来自20名腹部癌症患者的100个分数CBCT评估了该方法,并在保持测试中来自21名不同腹部癌症患者的队列中的105个分数CBCT。从定性上讲,注册结果显示了变形的CBCT图像与目标CBCT图像之间的对齐。定量地,在基准标记和手动确定的地标计算的平均目标注册误差(TRE)为1.91+-1.11 mm。变形CBCT和目标CBCT之间的平均平均绝对误差(MAE),归一化的跨相关性(NCC)分别为33.42+-7.48 HU,0.94+-0.04。这种有希望的注册方法可以提供快速准确的纵向CBCT对准,以促进分流的解剖变化分析和预测。
translated by 谷歌翻译
联合学习(FL)是一个新的分布式机器学习框架,可以在不收集用户的私人数据的情况下获得可靠的协作培训。但是,由于FL的频繁沟通和平均聚合策略,他们会遇到挑战统计多样性数据和大规模模型。在本文中,我们提出了一个个性化的FL框架,称为基于Tensor分解的个性化联合学习(TDPFED),在该框架中,我们设计了一种具有张力的线性层和卷积层的新颖的张力局部模型,以降低交流成本。 TDPFED使用双级损失函数来通过控制个性化模型和张力的本地模型之间的差距来使全球模型学习的个性化模型优化。此外,有效的分布式学习策略和两种不同的模型聚合策略是为拟议的TDPFED框架设计的。理论融合分析和彻底的实验表明,我们提出的TDPFED框架在降低交流成本的同时实现了最新的性能。
translated by 谷歌翻译
在多种方案中,多幕科建议专门为用户检索相关项目,这在工业推荐系统中无处不在。这些方案享有用户和项目中的一部分重叠,而不同方案的分布则不同。多阶段建模的关键点是有效地最大程度地利用全幕纳罗来信息,并在多种情况下为用户和项目生成适应性表示。我们总结了三个实用挑战,这些挑战无法很好地解决多幕科建模:(1)在多种情况下缺乏细粒度和脱钩的信息传输控制。 (2)整个空间样品的开发不足。 (3)项目的多幕科代表性分解问题。在本文中,我们提出了一种情景自适应和自我监督(SASS)模型,以解决上述三个挑战。具体而言,我们使用场景自适应门单元设计了多层场景自适应转移(ML-SAT)模块,以相当细粒度且脱钩的方式选择并融合从整个场景到单个场景的有效传输信息。为了充分利用整个空间样品的功能,引入了包括预训练和微调在内的两阶段训练过程。预训练阶段是基于场景监督的对比学习任务,并从标记和未标记的数据空间中绘制的培训样本。该模型是在用户端和项目方面对称创建的,因此我们可以在不同情况下获得项目的区分表示。公共和工业数据集的广泛实验结果证明了SASS模型比最先进的方法的优越性。该模型还可以在在线A/B测试中平均每位用户的观看时间提高8.0%以上。
translated by 谷歌翻译
本文回顾了AIM 2022上压缩图像和视频超级分辨率的挑战。这项挑战包括两条曲目。轨道1的目标是压缩图像的超分辨率,轨迹〜2靶向压缩视频的超分辨率。在轨道1中,我们使用流行的数据集DIV2K作为培训,验证和测试集。在轨道2中,我们提出了LDV 3.0数据集,其中包含365个视频,包括LDV 2.0数据集(335个视频)和30个其他视频。在这一挑战中,有12支球队和2支球队分别提交了赛道1和赛道2的最终结果。所提出的方法和解决方案衡量了压缩图像和视频上超分辨率的最先进。提出的LDV 3.0数据集可在https://github.com/renyang-home/ldv_dataset上找到。此挑战的首页是在https://github.com/renyang-home/aim22_compresssr。
translated by 谷歌翻译