Current computer vision models, unlike the human visual system, cannot yet achieve general-purpose visual understanding. Existing efforts to create a general vision model are limited in the scope of assessed tasks and offer no overarching framework to perform them holistically. We present a new comprehensive benchmark, General-purpose Visual Understanding Evaluation (G-VUE), covering the full spectrum of visual cognitive abilities with four functional domains $\unicode{x2014}$ Perceive, Ground, Reason, and Act. The four domains are embodied in 11 carefully curated tasks, from 3D reconstruction to visual reasoning and manipulation. Along with the benchmark, we provide a general encoder-decoder framework to allow for the evaluation of arbitrary visual representation on all 11 tasks. We evaluate various pre-trained visual representations with our framework and observe that (1) Transformer-based visual backbone generally outperforms CNN-based backbone on G-VUE, (2) visual representations from vision-language pre-training are superior to those with vision-only pre-training across visual tasks. With G-VUE, we provide a holistic evaluation standard to motivate research toward building general-purpose visual systems via obtaining more general-purpose visual representations.
translated by 谷歌翻译
随着几个行业正在朝着建模大规模的3D虚拟世界迈进,因此需要根据3D内容的数量,质量和多样性来扩展的内容创建工具的需求变得显而易见。在我们的工作中,我们旨在训练Parterant 3D生成模型,以合成纹理网格,可以通过3D渲染引擎直接消耗,因此立即在下游应用中使用。 3D生成建模的先前工作要么缺少几何细节,因此在它们可以生成的网格拓扑中受到限制,通常不支持纹理,或者在合成过程中使用神经渲染器,这使得它们在常见的3D软件中使用。在这项工作中,我们介绍了GET3D,这是一种生成模型,该模型直接生成具有复杂拓扑,丰富几何细节和高保真纹理的显式纹理3D网格。我们在可区分的表面建模,可区分渲染以及2D生成对抗网络中桥接了最新成功,以从2D图像集合中训练我们的模型。 GET3D能够生成高质量的3D纹理网格,从汽车,椅子,动物,摩托车和人类角色到建筑物,对以前的方法进行了重大改进。
translated by 谷歌翻译
文本表示的预培训(PT)已成功应用于低资源神经机器翻译(NMT)。但是,它通常无法在资源丰富的NMT上获得显着的收益(有时甚至更糟),与其随机定位(RI)对应物相当。我们迈出了第一步,通过两个探测分析来研究资源丰富的场景中PT和RI之间的互补性,并发现:1)PT并不提高准确性,而是通过实现平坦的损失景观而不是RI的概括。 2)PT不是提高词汇选择的信心,而是通过分配更平滑的词汇概率分布而不是RI的词汇分布来提高词汇选择的信心。基于这些见解,我们建议将它们的互补性与模型融合算法相结合,该算法利用最佳传输来对齐PT和RI之间的神经元。对两个资源丰富的翻译基准的实验,WMT'17英语 - 中国(20m)和WMT'19英语 - 德国人(36m),表明PT和RI可以彼此很好地互补,可以实现实质性的改进,考虑到这两个翻译准确性,考虑到同时的翻译准确性,概括和负多样性。探测工具和代码的发布:https://github.com/zanchangtong/ptvsri。
translated by 谷歌翻译
二进制神经网络(BNN)是卷积神经网络(CNN)的极端量化版本,其所有功能和权重映射到仅1位。尽管BNN节省了大量的内存和计算需求以使CNN适用于边缘或移动设备,但由于二进制后的表示能力降低,BNN遭受了网络性能的下降。在本文中,我们提出了一个新的可更换且易于使用的卷积模块reponv,该模块reponv通过复制输入或沿通道维度的输出来增强特征地图,而不是$ \ beta $ times,而没有额外的参数和卷积计算费用。我们还定义了一组Reptran规则,可以在整个BNN模块中使用Repconv,例如二进制卷积,完全连接的层和批处理归一化。实验表明,在Reptran转换之后,一组高度引用的BNN与原始BNN版本相比,实现了普遍的性能。例如,Rep-Recu-Resnet-20的前1位准确性,即REPBCONV增强的RECU-RESNET-20,在CIFAR-10上达到了88.97%,比原始网络高1.47%。 Rep-Adambnn-Reactnet-A在Imagenet上获得了71.342%的TOP-1精度,这是BNN的最新结果。代码和型号可在以下网址提供:https://github.com/imfinethanks/rep_adambnn。
translated by 谷歌翻译
对于多语言序列到序列预审预周序模型(多语言SEQ2SEQ PLM),例如姆巴特(Mbart),自制的预处理任务接受了多种单语言的培训,例如25种来自CommonCrawl的语言,而下游的跨语言任务通常在双语语言子集上进行,例如英语 - 德国人,存在数据差异,即领域的差异,以及跨语言学习客观差异,即在训练和填充阶段之间的任务差异。为了弥合上述跨语言域和任务差距,我们将使用额外的代码切换恢复任务扩展了香草预后管道。具体而言,第一阶段采用自我监督的代码转换还原任务作为借口任务,从而允许多语言SEQ2SEQ PLM获取一些域内对齐信息。在第二阶段,我们正常在下游数据上微调模型。 NLG评估(12个双语翻译任务,30个零射击任务和2项跨语言摘要任务)和NLU评估(7个跨语性自然语言推理任务)的实验表明,我们的模型超过了强大的基线MBART,具有标准的FINETUNNING,这表明了我们的模型策略,一致。分析表明,我们的方法可以缩小跨语性句子表示的欧几里得距离,并通过微不足道的计算成本改善模型概括。我们在:https://github.com/zanchangtong/csr4mbart上发布代码。
translated by 谷歌翻译
解决纳米级的形态学化相变对各种学科的许多科学和工业应用至关重要。通过组合全场传输X射线显微镜(TXM)和X射线吸收附近边缘结构(XANES)的TXM-XANES成像技术是通过获取具有多能量X的一系列显微镜图像来操作的新兴工具 - 接合并配合以获得化学图。然而,由于系统误差和用于快速采集的低曝光照明,其能力受到差的信噪比差的限制。在这项工作中,通过利用TXM-XANES成像数据的内在属性和子空间建模,我们引入了一种简单且坚固的去噪方法来提高图像质量,这使得能够快速和高灵敏度的化学成像。对合成和实时数据集的广泛实验证明了该方法的优越性。
translated by 谷歌翻译
我们为无随机动态系统的数据驱动模拟提供了一个深度学习模型,而无需分布假设。深度学习模型包括一个经常性的神经网络,旨在学习时间行进结构,以及从随机动力系统的概率分布来学习和采样的生成的对抗性网络。虽然生成的对策网络提供了一个强大的工具来建模复杂的概率分布,但训练通常在没有适当的正则化的情况下失败。在这里,我们提出了一种基于顺序推理问题的一致性条件的生成对抗性网络的正则化策略。首先,最大平均差异(MMD)用于实施随机过程的条件和边际分布之间的一致性。然后,通过使用MMD或来自多个鉴别器来规范多步预测的边缘分布。通过使用具有复杂噪声结构的三个随机过程来研究所提出的模型的行为。
translated by 谷歌翻译
In this paper, we study the use of deep Transformer translation model for the CCMT 2022 Chinese-Thai low-resource machine translation task. We first explore the experiment settings (including the number of BPE merge operations, dropout probability, embedding size, etc.) for the low-resource scenario with the 6-layer Transformer. Considering that increasing the number of layers also increases the regularization on new model parameters (dropout modules are also introduced when using more layers), we adopt the highest performance setting but increase the depth of the Transformer to 24 layers to obtain improved translation quality. Our work obtains the SOTA performance in the Chinese-to-Thai translation in the constrained evaluation.
translated by 谷歌翻译
Given a natural language that describes the user's demands, the NL2Code task aims to generate code that addresses the demands. This is a critical but challenging task that mirrors the capabilities of AI-powered programming. The NL2Code task is inherently versatile, diverse and complex. For example, a demand can be described in different languages, in different formats, and at different levels of granularity. This inspired us to do this survey for NL2Code. In this survey, we focus on how does neural network (NN) solves NL2Code. We first propose a comprehensive framework, which is able to cover all studies in this field. Then, we in-depth parse the existing studies into this framework. We create an online website to record the parsing results, which tracks existing and recent NL2Code progress. In addition, we summarize the current challenges of NL2Code as well as its future directions. We hope that this survey can foster the evolution of this field.
translated by 谷歌翻译
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. Despite being the main challenge of the task compared to extractive QA, current numerical reasoning method simply uses LSTM to autoregressively decode program sequences, and each decoding step produces either an operator or an operand. However, the step-by-step decoding suffers from exposure bias, and the accuracy of program generation drops sharply with progressive decoding. In this paper, we propose a non-autoregressive program generation framework, which facilitates program generation in parallel. Our framework, which independently generates complete program tuples containing both operators and operands, can significantly boost the speed of program generation while addressing the error accumulation issue. Our experiments on the MultiHiertt dataset shows that our model can bring about large improvements (+7.97 EM and +6.38 F1 points) over the strong baseline, establishing the new state-of-the-art performance, while being much faster (21x) in program generation. The performance drop of our method is also significantly smaller than the baseline with increasing numbers of numerical reasoning steps.
translated by 谷歌翻译