Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based cost models perform significantly better than other methods, they still fall short and suffer from the following problems. First, their feature extraction heavily relies on expert-level domain knowledge in hardware architectures. Even so, the extracted features are often unsatisfactory and require separate considerations for CPUs and GPUs. Second, a cost model trained on one hardware platform usually performs poorly on another, a problem we call cross-hardware unavailability. In order to address these problems, we propose TLP and MTLTLP. TLP is a deep learning-based cost model that facilitates tensor program tuning. Instead of extracting features from the tensor program itself, TLP extracts features from the schedule primitives. We treat schedule primitives as tensor languages. TLP is thus a Tensor Language Processing task. In this way, the task of predicting the tensor program latency through the cost model is transformed into a natural language processing (NLP) regression task. MTL-TLP combines Multi-Task Learning and TLP to cope with the cross-hardware unavailability problem. We incorporate these techniques into the Ansor framework and conduct detailed experiments. Results show that TLP can speed up the average search time by 9.1X and 3.0X on CPU and GPU workloads, respectively, compared to the state-of-the-art implementation. MTL-TLP can achieve a speed-up of 4.7X and 2.9X on CPU and GPU workloads, respectively, using only 7% of the target hardware data.
translated by 谷歌翻译
基于激光传感器的同时定位和映射(SLAM)已被移动机器人和自动驾驶汽车广泛采用。这些大满贯系统需要用有限的计算资源来支持准确的本地化。特别是,点云注册,即,在全球坐标框架中在多个位置收集的多个LIDAR扫描匹配和对齐的过程被视为SLAM的瓶颈步骤。在本文中,我们提出了一种功能过滤算法Pfilter,可以过滤无效的功能,因此可以大大减轻这种瓶颈。同时,由于精心策划的特征点,总体注册精度也得到了提高。我们将PFILTER集成到公认的扫描到映射激光射击轨道框架F-LOAM,并评估其在KITTI数据集中的性能。实验结果表明,pfilter可以删除本地特征图中约48.4%的点,并将扫描中的特征点平均减少19.3%,从而节省每帧的处理时间20.9%。同时,我们将准确性提高了9.4%。
translated by 谷歌翻译
在这项工作中,我们探索了用于视觉接地的整洁而有效的基于变压器的框架。先前的方法通常解决了视觉接地的核心问题,即具有手动设计的机制,即多模式融合和推理。这样的启发式设计不仅复杂化,而且使模型容易过度拟合特定的数据分布。为了避免这种情况,我们首先提出了TransVG,该TransVG通过变压器建立了多模式的对应关系,并通过直接回归框坐标来定位引用区域。我们从经验上表明,复杂的融合模块可以用具有更高性能的变压器编码层的简单堆栈代替。但是,TransVG中的核心融合变压器是针对Uni-Modal编码器的独立性,因此应在有限的视觉接地数据上从头开始训练,这使得很难优化并导致次优性能。为此,我们进一步介绍了TransVG ++以进行两倍的改进。一方面,我们通过利用Vision Transformer(VIT)进行视觉功能编码来将框架升级到一个纯粹的基于变压器的框架。对于另一个人来说,我们设计了语言有条件的视觉变压器,以去除外部融合模块,并重用Uni-Modal vit进行中间层的视觉融合。我们对五个普遍数据集进行了广泛的实验,并报告一系列最先进的记录。
translated by 谷歌翻译
它得到了很好的认识到,从深度感知的LIDAR点云和语义富有的立体图像中融合互补信息将有利于3D对象检测。然而,探索稀疏3D点和密集2D像素之间固有的不自然相互作用并不重要。为了简化这种困难,最近的建议通常将3D点投影到2D图像平面上以对图像数据进行采样,然后聚合点处的数据。然而,这种方法往往遭受点云和RGB图像的分辨率之间的不匹配,导致次优性能。具体地,作为多模态数据聚合位置的稀疏点导致高分辨率图像的严重信息丢失,这反过来破坏了多传感器融合的有效性。在本文中,我们呈现VPFNET - 一种新的架构,可以在“虚拟”点处巧妙地对齐和聚合点云和图像数据。特别地,它们的密度位于3D点和2D像素的密度之间,虚拟点可以很好地桥接两个传感器之间的分辨率间隙,从而保持更多信息以进行处理。此外,我们还研究了可以应用于点云和RGB图像的数据增强技术,因为数据增强对迄今为止对3D对象探测器的贡献不可忽略。我们对Kitti DataSet进行了广泛的实验,与最先进的方法相比,观察到了良好的性能。值得注意的是,我们的VPFNET在KITTI测试集上实现了83.21 \%中等3D AP和91.86 \%适度的BEV AP,自2021年5月21日起排名第一。网络设计也考虑了计算效率 - 我们可以实现FPS 15对单个NVIDIA RTX 2080TI GPU。该代码将用于复制和进一步调查。
translated by 谷歌翻译
通过直接将感知输入映射到机器人控制命令中,深入的强化学习(DRL)算法已被证明在机器人导航中有效,尤其是在未知环境中。但是,大多数现有方法忽略导航中的局部最小问题,从而无法处理复杂的未知环境。在本文中,我们提出了第一个基于DRL的导航方法,该方法由具有连续动作空间,自适应向前模拟时间(AFST)的SMDP建模,以克服此问题。具体而言,我们通过修改其GAE来更好地估计SMDP中的策略梯度,改善了指定SMDP问题的分布式近端策略优化(DPPO)算法。我们在模拟器和现实世界中评估了我们的方法。
translated by 谷歌翻译
传统的城市规划要求城市专家在许多建筑限制下花费大量时间和精力制定最佳的城市计划。深层生成学习的非凡富有想象力为翻新城市规划提供了希望。尽管已经检查了自动化的城市规划师,但由于以下情况,它们受到限制:1)忽略人类在城市规划中的要求; 2)省略城市规划中的空间层次结构,以及3)缺乏许多城市计划数据样本。为了克服这些局限性,我们提出了一个新颖的,深厚的人类建筑的城市规划师。在初步工作中,我们将其提出为编码器范式。编码器是学习周围环境,人类指示和土地使用配置的信息分布。解码器是重建土地使用配置和相关的城市功能区域。重建过程将捕获功能区和空间网格之间的空间层次结构。同时,我们引入了一种变异的高斯机制来减轻数据稀疏问题。即使早期的工作导致了良好的结果,但生成的性能仍然不稳定,因为捕获空间层次结构的方式可能会导致不清楚的优化方向。在此期刊版本中,我们提出了一个基于生成的对抗网络(GAN)的层叠的深层生成框架,以解决此问题,灵感来自城市专家的工作流程。特别是,第一个gan的目的是根据人类指示和周围环境的信息来建立城市功能区域。第二个GAN将基于已构造的功能区域产生土地使用构型。此外,我们为增强数据样本提供了调节增强模块。最后,我们进行了广泛的实验以验证工作的功效。
translated by 谷歌翻译
多视图无监督的特征选择(MUF)已被证明是一种有效的技术,可降低多视图未标记数据的维度。现有方法假定所有视图都已完成。但是,多视图数据通常不完整,即,某些视图中显示了一部分实例,但并非所有视图。此外,学习完整的相似性图,作为现有MUFS方法中重要的有前途的技术,由于缺少的观点而无法实现。在本文中,我们提出了一个基于互补的和共识学习的不完整的多视图无监督的特征选择方法(C $^{2} $ IMUFS),以解决上述问题。具体而言,c $^{2} $ imufs将功能选择集成到扩展的加权非负矩阵分解模型中,配备了自适应学习视图和稀疏的$ \ ell_ {2,p} $ - norm-norm,它可以提供更好的提供适应性和灵活性。通过从不同视图得出的多个相似性矩阵的稀疏线性组合,介绍了互补学习引导的相似性矩阵重建模型,以在每个视图中获得完整的相似性图。此外,c $^{2} $ imufs学习了跨不同视图的共识聚类指示器矩阵,并将其嵌入光谱图术语中以保留本地几何结构。现实世界数据集的全面实验结果证明了与最新方法相比,C $^{2} $ IMUF的有效性。
translated by 谷歌翻译
Multi-view unsupervised feature selection has been proven to be efficient in reducing the dimensionality of multi-view unlabeled data with high dimensions. The previous methods assume all of the views are complete. However, in real applications, the multi-view data are often incomplete, i.e., some views of instances are missing, which will result in the failure of these methods. Besides, while the data arrive in form of streams, these existing methods will suffer the issues of high storage cost and expensive computation time. To address these issues, we propose an Incremental Incomplete Multi-view Unsupervised Feature Selection method (I$^2$MUFS) on incomplete multi-view streaming data. By jointly considering the consistent and complementary information across different views, I$^2$MUFS embeds the unsupervised feature selection into an extended weighted non-negative matrix factorization model, which can learn a consensus clustering indicator matrix and fuse different latent feature matrices with adaptive view weights. Furthermore, we introduce the incremental leaning mechanisms to develop an alternative iterative algorithm, where the feature selection matrix is incrementally updated, rather than recomputing on the entire updated data from scratch. A series of experiments are conducted to verify the effectiveness of the proposed method by comparing with several state-of-the-art methods. The experimental results demonstrate the effectiveness and efficiency of the proposed method in terms of the clustering metrics and the computational cost.
translated by 谷歌翻译
融合技术是多模式情绪分析中的关键研究主题。最近的关注的融合表明了基于简单的操作融合的进步。然而,这些融合作品采用单规模,即令牌级或话语水平,单峰代表。这种单尺度融合是次优,因为不同的模态应该以不同的粒度对齐。本文提出了名为Scalevlad的融合模型,从文本,视频和音频中收集多尺度表示,与本地聚合描述符的共享向量,以改善未对准的多模式情绪分析。这些共享向量可以被视为共享主题以对齐不同的模态。此外,我们提出了一种自我监督的移位聚类损失,以保持样本之间的融合特征差异化。底部是对应于三个模态的三个变压器编码器,并且从融合模块产生的聚合特征将馈送到变压器加上完成任务预测的完全连接。在三个流行的情感分析基准,IEMocap,MOSI和MOSEI的实验,证明了基准的显着收益。
translated by 谷歌翻译
Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.
translated by 谷歌翻译