图像检索系统可帮助用户实时浏览和搜索。随着云计算的兴起,检索任务通常外包到云服务器。但是,由于云服务器无法完全信任,因此云场景带来了隐私保护的艰巨挑战。为此,已经开发了基于图像加密的图像检索方案,首先是从密码图像中提取特征,然后根据这些功能构建检索模型。然而,大多数现有方法提取浅特征和设计微不足道的检索模型,从而导致密码图像的表现不足。在本文中,我们提出了一种名为“加密视觉变压器”(EVIT)的新型范式,该范式提高了密码图像的判别性表述能力。首先,为了捕获全面的统治信息,我们从密码图像中提取多级局部长度序列和全局Huffman代码频率特征,这些序列在JPEG压缩过程中由流密码加密。其次,我们将基于视觉变压器的检索模型设计为与多层次功能相结合,并提出了两种自适应数据增强方法,以提高检索模型的表示能力。我们的建议很容易通过自我监督的对比学习方式来适应无监督和监督的环境。广泛的实验表明,EVIT既可以实现出色的加密和检索性能,从而超过了当前方案,从而在大幅度的检索准确性方面优于当前方案,同时有效地保护图像隐私。代码可在\ url {https://github.com/onlinehuazai/evit}上公开获得。
translated by 谷歌翻译
基础模型正在成为主要的深度学习技术。由于模型参数和训练数据集的大规模,预处理基础模型始终耗时。除了计算密集型外,培训过程还非常密集和沟通密集。这些功能使得需要应用3D并行性,该平行性整合数据并行性,管道模型并行性和张量模型并行性,以实现高训练效率。为了实现这一目标,开发了一些自定义软件框架,例如Megatron-LM和DeepSpeed。但是,当前的3D平行框架仍然符合两个问题:i)它们对模型开发人员不透明,这些开发人员需要手动修改模型以并行化培训。 ii)它们对计算,GPU存储器和网络带宽的利用不足。我们提出了Merak,这是一个自动化的3D并行性深度学习培训框架,并具有高度资源利用。 Merak会自动使用自动模型分区仪部署,该分区仪在模型的代理表示上使用图形sharding算法。 Merak还提出了非侵入性的API,用于通过最小的代码修改来扩展基础模型培训。此外,我们在Merak设计了高性能的3D平行运行时引擎。它使用多种技术来利用可用的培训资源,包括移动的关键路径管道时间表,该计划带来了更高的计算利用率,阶段感知的重新计算,可利用空闲工作者的记忆以及子额定张量的模型并行性,这些模型并联与通信和计算重叠。 64 GPU的实验显示,Merak可以加快在最新的3D平行性框架上,具有1.5、2.5、8.3和20亿的模型框架,最高可达1.42x,1.39x,1.43x和1.61 x分别。
translated by 谷歌翻译
有限的GPU记忆资源阻碍了深度神经网络的进一步发展。因此,高度要求GPU内存资源的优化。通常应用交换和重新计算,以更好地利用GPU记忆。但是,作为一个新兴领域,仍然存在一些挑战:1)静态和动态方法的重新计算效率受到限制。 2)交换需要手动卸载参数,这会产生巨大的时间成本。 3)没有这种动态和细粒的方法,涉及张量与当今的张量重新组件一起交换。为了纠正上述问题,我们提出了一个名为Delta(动态张量卸载和重新组件)的新型调度程序经理。据我们所知,我们是第一个在没有用户监督的情况下进行张量交换和张量重新组合的合理的动态运行时间调度程序。在Delta中,我们提出了一种过滤器算法,以选择要从GPU内存中释放出来的最佳张量,并提出导演算法,以选择每个张量的适当动作。此外,故意考虑预取和重叠以克服交换和重新计算张量引起的时间成本。实验结果表明,DELTA不仅节省了40%-70%的GPU记忆,从而超过了最新方法,而且还获得了可比的收敛结果,并获得了可接受的时间延迟。此外,与基准相比,当训练Resnet-101训练Resnet-101时,Delta在训练Resnet-50和2.25 $ \ times $时获得2.04 $ \ times $最大批量。此外,我们实验中的交换成本和重新计算成本之间的比较表明,在张量交换和张量重新计算上制定合理的动态调度程序的重要性,这在某些相关工作中反驳了交换应该是第一个也是最好的选择。
translated by 谷歌翻译
Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabilities of image labels conditioned by their features similarity in a contrastive learning setting. This contrastive Bayesian analysis leads to a new loss function for deep metric learning. To improve the generalization capability of the proposed method onto new classes, we further extend the contrastive Bayesian loss with a metric variance constraint. Our experimental results and ablation studies demonstrate that the proposed contrastive Bayesian metric learning method significantly improves the performance of deep metric learning in both supervised and pseudo-supervised scenarios, outperforming existing methods by a large margin.
translated by 谷歌翻译
现有的多尺度解决方案会导致仅增加接受场大小的风险,同时忽略小型接受场。因此,有效构建自适应神经网络以识别各种空间尺度对象是一个具有挑战性的问题。为了解决这个问题,我们首先引入一个新的注意力维度,即除了现有的注意力维度(例如渠道,空间和分支)之外,并提出了一个新颖的选择性深度注意网络,以对称地处理各种视觉中的多尺度对象任务。具体而言,在给定神经网络的每个阶段内的块,即重新连接,输出层次功能映射共享相同的分辨率但具有不同的接收场大小。基于此结构属性,我们设计了一个舞台建筑模块,即SDA,其中包括树干分支和类似SE的注意力分支。躯干分支的块输出融合在一起,以通过注意力分支指导其深度注意力分配。根据提出的注意机制,我们可以动态选择不同的深度特征,这有助于自适应调整可变大小输入对象的接收场大小。这样,跨块信息相互作用会导致沿深度方向的远距离依赖关系。与其他多尺度方法相比,我们的SDA方法结合了从以前的块到舞台输出的多个接受场,从而提供了更广泛,更丰富的有效接收场。此外,我们的方法可以用作其他多尺度网络以及注意力网络的可插入模块,并创造为SDA- $ x $ net。它们的组合进一步扩展了有效的接受场的范围,可以实现可解释的神经网络。我们的源代码可在\ url {https://github.com/qingbeiguo/sda-xnet.git}中获得。
translated by 谷歌翻译
分布式数据并行训练已被广泛用于深神经网络(DNN)模型。尽管当前的深度学习(DL)框架对于图像分类模型(例如图像分类模型)的密集模型很好地扩展了,但我们发现这些DL框架对于具有高度稀疏嵌入表的稀疏模型(NLP)模型(NLP)模型(NLP)模型具有相对较低的可扩展性。大多数现有作品忽略了模型参数的稀疏性,因此遭受了重要但不必要的沟通开销。在本文中,我们提出了Ablace,这是一个有效的沟通框架,以加快稀疏模型分布式培训的通信。 Embrace引入了稀疏感知的混合通信,将AlltoAll和模型并行置于数据并行训练中,以减少高度稀疏参数的交流开销。为了有效地重叠稀疏的通信与后向前和前向计算,采用进一步设计的2D通信调度方法,该方法优化了模型计算过程,放松嵌入式的依赖性,并计划以优先级的排队来安排每个嵌入行的稀疏通信。我们已经基于Pytorch和Horovod实施了Embrace的原型,并通过四个代表性的NLP模型进行了全面的评估。实验结果表明,与最先进的分布式训练基线相比,Embrace的速度高达2.41倍。
translated by 谷歌翻译
分布式随机梯度下降(SGD)方法已广泛应用于大型深度学习,梯度集体方法至关重要,以确保分布式深度学习系统的培训可扩展性。已广泛采用分布式SGD过程广泛采用诸如解释的集体通信,以减少通信时间。但是,allreduce会引发大带宽资源,而在许多情况下大多数梯度稀疏,因为许多梯度值是零,并且应该有效地压缩以用于节省带宽。为了减少稀疏梯度通信开销,我们提出了一种稀疏的剪影减速器(S2减速器),这是一种具有收敛保证的新型草图的稀疏梯度聚合方法。 S2减速机仅通过Count-Sketch和Bitmap压缩非零梯度来降低通信成本,并实现有效的已有SGD培训的有效恢复运算符。我们在五种培训模型中对四种最先进的方法进行广泛的评估。我们的结果表明,S2减速机收敛到相同的准确性,降低了81 \%稀疏通信开销,与最先进的方法相比,实现了1.8 $ \ times $ Speedup。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
translated by 谷歌翻译