One of the major challenges of machine translation (MT) is ambiguity, which can in some cases be resolved by accompanying context such as an image. However, recent work in multimodal MT (MMT) has shown that obtaining improvements from images is challenging, limited not only by the difficulty of building effective cross-modal representations but also by the lack of specific evaluation and training data. We present a new MMT approach based on a strong text-only MT model, which uses neural adapters and a novel guided self-attention mechanism and which is jointly trained on both visual masking and MMT. We also release CoMMuTE, a Contrastive Multilingual Multimodal Translation Evaluation dataset, composed of ambiguous sentences and their possible translations, accompanied by disambiguating images corresponding to each translation. Our approach obtains competitive results over strong text-only models on standard English-to-French benchmarks and outperforms these baselines and state-of-the-art MMT systems with a large margin on our contrastive test set.
translated by 谷歌翻译
In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer knowledge-intensive queries. REVEAL consists of four key components: the memory, the encoder, the retriever and the generator. The large-scale memory encodes various sources of multimodal world knowledge (e.g. image-text pairs, question answering pairs, knowledge graph triplets, etc) via a unified encoder. The retriever finds the most relevant knowledge entries in the memory, and the generator fuses the retrieved knowledge with the input query to produce the output. A key novelty in our approach is that the memory, encoder, retriever and generator are all pre-trained end-to-end on a massive amount of data. Furthermore, our approach can use a diverse set of multimodal knowledge sources, which is shown to result in significant gains. We show that REVEAL achieves state-of-the-art results on visual question answering and image captioning.
translated by 谷歌翻译
Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining architectures and objectives within the masked autoencoding framework, motivated by the success of similar methods in natural language and image understanding. We show that we can achieve significant improvements on audiovisual downstream classification tasks, surpassing the state-of-the-art on VGGSound and AudioSet. Furthermore, we can leverage our audiovisual pretraining scheme for multiple unimodal downstream tasks using a single audiovisual pretrained model. We additionally demonstrate the transferability of our representations, achieving state-of-the-art audiovisual results on Epic Kitchens without pretraining specifically for this dataset.
translated by 谷歌翻译
Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level objectives, e.g. image classification, image-text alignment a la CLIP, or self-supervised contrastive learning. These objectives do not model spatial information, which might be suboptimal when finetuning on downstream tasks with spatial reasoning. In this work, we propose to pretrain networks for semantic segmentation by predicting the relative location of image parts. We formulate this task as a classification problem where each patch in a query view has to predict its position relatively to another reference view. We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query. Our experiments show that this location-aware (LOCA) self-supervised pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
translated by 谷歌翻译
强化学习(RL)和轨迹优化(TO)具有强大的互补优势。一方面,RL方法能够直接从数据中学习全球控制策略,但通常需要大型样本量以正确地收敛于可行的策略。另一方面,对方法能够利用从模拟器提取的基于梯度的信息,以快速收敛到局部最佳控制轨迹,该轨迹仅在解决方案附近有效。在过去的十年中,几种方法旨在充分结合两类方法,以获得两全其美的最佳选择。从这一研究开始,我们提出了这些方法的一些改进,以更快地学习全球控制政策,尤其是通过通过Sobolev学习来利用敏感性信息,并增强了Lagrangian技术来实施与政策学习之间的共识。我们通过与文献中的现有方法进行比较,评估了这些改进对机器人技术各种经典任务的好处。
translated by 谷歌翻译
在人类环境中,预计在简单的自然语言指导下,机器人将完成各种操纵任务。然而,机器人的操纵极具挑战性,因为它需要精细颗粒的运动控制,长期记忆以及对以前看不见的任务和环境的概括。为了应对这些挑战,我们提出了一种基于统一的变压器方法,该方法考虑了多个输入。特别是,我们的变压器体系结构集成了(i)自然语言指示和(ii)多视图场景观察,而(iii)跟踪观察和动作的完整历史。这种方法使历史和指示之间的学习依赖性可以使用多个视图提高操纵精度。我们评估我们的方法在具有挑战性的RLBench基准和现实世界机器人方面。值得注意的是,我们的方法扩展到74个不同的RLBench任务,并超越了最新的现状。我们还解决了指导条件的任务,并证明了对以前看不见的变化的出色概括。
translated by 谷歌翻译
在视觉和语言导航(VLN)中,按照自然语言指令在现实的3D环境中需要具体的代理。现有VLN方法的一个主要瓶颈是缺乏足够的培训数据,从而导致对看不见的环境的概括不令人满意。虽然通常会手动收集VLN数据,但这种方法很昂贵,并且可以防止可扩展性。在这项工作中,我们通过建议从HM3D自动创建900个未标记的3D建筑物的大规模VLN数据集来解决数据稀缺问题。我们为每个建筑物生成一个导航图,并通过交叉视图一致性从2D传输对象预测,从2D传输伪3D对象标签。然后,我们使用伪对象标签来微调一个预处理的语言模型,作为减轻教学生成中跨模式差距的提示。在导航环境和说明方面,我们生成的HM3D-AUTOVLN数据集是比现有VLN数据集大的数量级。我们通过实验表明,HM3D-AUTOVLN显着提高了所得VLN模型的概括能力。在SPL指标上,我们的方法分别在Reverie和DataSet的看不见的验证分裂分别对艺术的状态提高了7.1%和8.1%。
translated by 谷歌翻译
寻找特定任务说明的YouTube用户可能会花费很长时间浏览内容,以寻找与他们需求相匹配的正确视频。创建视觉摘要(视频的删节版本)为观众提供了快速概述,并大大减少了搜索时间。在这项工作中,我们专注于总结教学视频,这​​是视频摘要的探索领域。与通用视频相比,可以将教学视频解析为语义上有意义的细分,这些细分与所示任务的重要步骤相对应。现有的视频摘要数据集依靠手动框架级注释,使其主观且大小有限。为了克服这一点,我们首先通过利用两个关键假设来自动为教学视频语料库生成伪摘要:(i)相关步骤可能会出现在相同任务(任务相关性)的多个视频中,并且(ii)它们更重要。可能由示威者口头描述(跨模式显着)。我们提出了一个教学视频摘要网络,该网络结合了上下文感知的时间视频编码器和段评分变压器。使用伪摘要作为弱监督,我们的网络为仅给出视频和转录语音的教学视频构建了视觉摘要。为了评估我们的模型,我们通过刮擦包含视频演示的Wikihow文章和步骤的视觉描绘,从而收集了高质量的测试集,即Wikihow摘要,从而使我们能够获得地面真实性摘要。我们的表现优于几个基线和这个新基准的最先进的视频摘要模型。
translated by 谷歌翻译
最近的工作取得了令人印象深刻的进展,从单眼颜色图像中联合重建手和操纵物体。现有的方法着重于两个替代表示,以参数网格或签名的距离字段(SDF)。一方面,参数模型可以以有限的形状变形和网格分辨率的成本从先验知识中受益。因此,网格模型可能无法精确地重建细节,例如手和物体的接触表面。另一方面,基于SDF的方法可以代表任意细节,但缺乏明确的先验。在这项工作中,我们旨在使用参数表示提供的PRIOR来改善SDF模型。特别是,我们提出了一个联合学习框架,该框架可以解散姿势和形状。我们从参数模型中获取手和对象摆姿势,并使用它们在3D空间中对齐SDF。我们表明,这种对齐的SDF可以更好地专注于重建形状细节,并提高手和物体的重建精度。我们评估了我们的方法,并在挑战性的OBMAN和DEXYCB基准方面证明了对最新技术的显着改善。
translated by 谷歌翻译
转移学习是用于训练小型目标数据集深层网络的主要范式。通常在大型``上游''数据集上预估计用于分类的模型,因为此类标签易于收集,然后在``下游''任务(例如动作本地化)上进行了填充,这些任务由于其较细粒度的注释而较小。在本文中,我们质疑这种方法,并提出共同访问 - 同时在多个``上游''和``下游''任务上训练单个模型。我们证明,在使用相同的数据总量时,共同传统的表现优于传统的转移学习,并且还展示了我们如何轻松地将方法扩展到多个``上游''数据集以进一步提高性能。尤其是,共同访问可以显着提高我们下游任务中稀有类别的性能,因为它具有正规化的效果,并使网络能够学习在不同数据集之间传输的功能表示。最后,我们观察到如何与公共,视频分类数据集共同进行,我们能够在挑战性的AVA和AVA-Kinetics数据集上实现最新的时空动作的结果,超过了最新的作品,这些作品的最新作品会发展出复杂的作品楷模。
translated by 谷歌翻译