跟踪牲畜的行为能够早期发现,从而预防现代动物农场的传染病。除了经济增益之外,这将减少畜牧业养殖的抗生素量,否则进入人类饮食恼怒的抗生素抗性的流行病 - 死亡的主要原因。我们可以使用标准的摄像机,在大多数现代农场提供,以监控牲畜。然而,大多数计算机视觉算法在这项任务上表现不佳,主要是因为(i)农场繁殖的动物看起来相同,缺乏任何明显的空间签名,(ii)没有现有的跟踪器对于长期保持稳健,并且(iii)真实 - 改变照明,频繁遮挡,不同的相机角度和动物尺寸的诸如变化的条件使得模型概括为概括。鉴于这些挑战,我们开发了针对小组母猪的端到端行为监测系统,以执行同时实例级分段,跟踪,动作识别和重新识别(星)任务。我们呈现StarFormer,这是第一个端到端的多目标牲畜监测框架,通过使用变压器架构了解分组猪的实例级嵌入式。对于基准测试,我们展示了一种仔细的策划数据集,包括视频序列,其中具有实例级界限框,实际室内养殖环境中的猪的分段,跟踪和活动分类。在明星任务上使用同步优化,我们展示了星际器优于培训的流行基线模型,为个人任务培训。
translated by 谷歌翻译
As language models have grown in parameters and layers, it has become much harder to train and infer with them on single GPUs. This is severely restricting the availability of large language models such as GPT-3, BERT-Large, and many others. A common technique to solve this problem is pruning the network architecture by removing transformer heads, fully-connected weights, and other modules. The main challenge is to discern the important parameters from the less important ones. Our goal is to find strong metrics for identifying such parameters. We thus propose two strategies: Cam-Cut based on the GradCAM interpretations, and Smooth-Cut based on the SmoothGrad, for calculating the importance scores. Through this work, we show that our scoring functions are able to assign more relevant task-based scores to the network parameters, and thus both our pruning approaches significantly outperform the standard weight and gradient-based strategies, especially at higher compression ratios in BERT-based models. We also analyze our pruning masks and find them to be significantly different from the ones obtained using standard metrics.
translated by 谷歌翻译
Real-world tasks are largely composed of multiple models, each performing a sub-task in a larger chain of tasks, i.e., using the output from a model as input for another model in a multi-model pipeline. A model like MATRa performs the task of Crosslingual Transliteration in two stages, using English as an intermediate transliteration target when transliterating between two indic languages. We propose a novel distillation technique, EPIK, that condenses two-stage pipelines for hierarchical tasks into a single end-to-end model without compromising performance. This method can create end-to-end models for tasks without needing a dedicated end-to-end dataset, solving the data scarcity problem. The EPIK model has been distilled from the MATra model using this technique of knowledge distillation. The MATra model can perform crosslingual transliteration between 5 languages - English, Hindi, Tamil, Kannada and Bengali. The EPIK model executes the task of transliteration without any intermediate English output while retaining the performance and accuracy of the MATra model. The EPIK model can perform transliteration with an average CER score of 0.015 and average phonetic accuracy of 92.1%. In addition, the average time for execution has reduced by 54.3% as compared to the teacher model and has a similarity score of 97.5% with the teacher encoder. In a few cases, the EPIK model (student model) can outperform the MATra model (teacher model) even though it has been distilled from the MATra model.
translated by 谷歌翻译
音译是NLP域中的一项任务,其中输出单词是使用任何外语字母编写的类似单词。如今,该系统已针对多种语言对开发,涉及英语作为源或目标单词,并在Google Translate和聊天机器人等多个地方部署。但是,在指示语言的领域进行的研究很少进行,将其译为其他指示语言。本文展示了一个基于变压器(具有一些修改)的多语言模型,该模型比该域中的所有现有模型都可以显着更高的性能和准确性,并且比最先进的模型获得了更好的结果。本文显示了一个模型,该模型可以在以下五种语言之间进行任何一对 - 英语,印地语,孟加拉语,卡纳达语和泰米尔语之间的音译。它适用于语言在任何书面任务中都是通信的障碍的情况。该模型击败了最先进的(对于上述五种语言中的所有对 - 英语,印地语,孟加拉语,卡纳达语和泰米尔语),并获得了80.7%的前1位准确性得分,比比当前最佳结果。此外,该模型在语音准确性方面达到了93.5%(音译主要是基于语音/声音的任务)。
translated by 谷歌翻译
据报道,传感器嵌入式手套系统需要仔细,耗时和精确的校准,以获得一致的可用数据。我们已经开发出低成本,基于Flex传感器的智能手套系统,可能是对数据手套的共同限制的弹性。该系统利用Arduino基础的微控制器以及每个手指上的单个柔性传感器。从Arduinos模拟到数字转换器的反馈可用于推断对象尺寸特性,每个单独的手指的反应相对于掌握物体的尺寸和形状不同。在这项工作中,我们在统计上区分了不同的半径的统计差异的静止物体,无论手套用户引入的变化如何。使用我们的传感器嵌入式手套系统,我们根据智能手套的每根手指的触觉传感器响应探索了物体分类的实用性。从五个手指平均柔性传感器读数中的每一个计算平均值的估计标准误差。与文献一致,我们发现物体形状,尺寸和柔性传感器读数之间存在系统的依赖性。当比较相同半径的球形和圆柱形物体时,从至少一个手指输出的传感器从至少一个手指输出。当传感各种尺寸的球体和气缸时,所有五个手指对每个形状具有明显不同的反应。我们认为,我们的发现可以用于机器学习模型,用于实时对象识别。
translated by 谷歌翻译
在这项工作中,我们提出了一种基于ADHOC网络的基于图卷积神经网络(GCN)的调度算法。特别是,我们考虑一个称为$ k $ -tolerant冲突图模型的广义干扰模型,并为众所周知的最大重量调度算法设计了有效的近似。这项工作的一个值得注意的特征是所提出的方法不需要标记的数据集(NP-难以计算)来训练神经网络。相反,我们设计了一种利用现有贪婪方法的损失函数,并列进GCN,提高了贪婪方法的性能。我们广泛的数值实验表明,使用我们的GCN方法,我们可以显着(4美元 - 20美元),提高传统贪婪方法的表现。
translated by 谷歌翻译