We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet. We find that this baseline has competitive performance with recent methods that leverage frozen visual representations trained on large-scale vision datasets.
translated by 谷歌翻译
Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which require expert knowledge to design, making it hard to scale up. To overcome this, we propose training with a large dataset of twenty-one thousand programs, each one generating a diverse set of synthetic images. These programs are short code snippets, which are easy to modify and fast to execute using OpenGL. The proposed dataset can be used for both supervised and unsupervised representation learning, and reduces the gap between pre-training with real and procedurally generated images by 38%.
translated by 谷歌翻译
Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications. Imposing such quasimetric structures in model representations has been shown to improve many tasks, including reinforcement learning (RL) and causal relation learning. In this work, we present four desirable properties in such quasimetric models, and show how prior works fail at them. We propose Interval Quasimetric Embedding (IQE), which is designed to satisfy all four criteria. On three quasimetric learning experiments, IQEs show strong approximation and generalization abilities, leading to better performance and improved efficiency over prior methods. Project Page: https://www.tongzhouwang.info/interval_quasimetric_embedding Quasimetric Learning Code Package: https://www.github.com/quasimetric-learning/torch-quasimetric
translated by 谷歌翻译
我们介绍了一种新的图像取证方法：将物理折射物（我们称为图腾）放入场景中，以保护该场景拍摄的任何照片。图腾弯曲并重定向光线，因此在单个图像中提供了多个（尽管扭曲）的多个（尽管扭曲）。防守者可以使用这些扭曲的图腾像素来检测是否已操纵图像。我们的方法通过估计场景中的位置并使用其已知的几何和材料特性来估算其位置，从而使光线通过图腾的光线不十障。为了验证图腾保护的图像，我们从图腾视点重建的场景与场景的外观从相机的角度来检测到不一致之处。这样的方法使对抗性操纵任务更加困难，因为对手必须以几何一致的方式对图腾和图像像素进行修改，而又不知道图腾的物理特性。与先前的基于学习的方法不同，我们的方法不需要在特定操作的数据集上进行培训，而是使用场景和相机的物理属性来解决取证问题。
translated by 谷歌翻译
我们的世界充满了不对称。重力和风能使与回来更容易到达地方。诸如家谱图和引文图之类的社会文物固有地定向。在强化学习和控制中，最佳目标策略很少是可逆的（对称性）。这些不对称结构支持的距离函数称为准函数。尽管出现了共同的外观，但对准对象的学习几乎没有研究。我们的理论分析表明，一种通用的学习算法，包括不受限制的多层感知器（MLP），事实证明，学习与培训数据一致的准学学都无法学习。相比之下，我们提出的泊松准嵌入（PQE）是第一个准学的学习配方，两者都可以通过基于梯度的优化来学习，并且具有强大的性能保证。在随机图，社交图和离线Q学习上进行的实验证明了其对许多常见基线的有效性。
translated by 谷歌翻译
将信号与噪声分开的能力以及干净的抽象对智能至关重要。有了这种能力，人类可以在不考虑所有可能的滋扰因素的情况下有效执行现实世界任务。人造代理可以做同样的事情？当噪音时，代理可以安全地丢弃什么样的信息？在这项工作中，我们根据可控性和与奖励的关系将野外信息分为四种类型，并将有用的信息归为可控和奖励相关的有用信息。该框架阐明了有关强化学习（RL）中的各种先前工作所删除的信息，并导致我们提出的学习方法，即学习一种已明确影响某些噪声分散注意器的DeNOCONE MDP。对DeepMind Control Suite和Robodesk的变体进行的广泛实验表明，我们的DeNocy World模型的表现优于仅使用原始观测值，并且超过了先前的工作，跨政策优化控制任务以及关节位置回归的非控制任务。
translated by 谷歌翻译
语言模型（LMS）显着提高端到端模型（E2E）模型在训练过程中很少见的单词的识别准确性，当时在浅融合或重新恢复设置中。在这项工作中，我们介绍了LMS在判别培训框架中学习混合自动回旋传感器（HAT）模型的研究，以减轻有关使用LMS的训练与推理差距。对于浅融合设置，我们在假设生成和损失计算过程中都使用LMS，而LM感知的MWER训练模型可实现10 \％的相对改进，比用标准MWER在语音搜索测试集中培训的模型相对改进，其中包含稀有单词。对于重新设置，我们学会了一个小型神经模块，以数据依赖性方式产生串联的融合权重。该模型与常规MWER训练的模型相同，但无需清除融合重量。
translated by 谷歌翻译
当前的视觉系统在巨大的数据集上培训，这些数据集具有成本：策良昂贵，他们继承了人类偏见，并且担心隐私和使用权。为了抵消这些成本，利息飙升，从更便宜的数据来源学习，如未标记的图像。在本文中，我们进一步逐步询问我们是否可以完全脱离真实的图像数据集，而是从噪声过程中学习。我们调查一套图像生成模型，从简单随机过程产生图像。然后将这些作为视觉表示学习者的培训数据，具有对比损失。我们在不同随机初始化下研究两种类型的噪声过程，统计图像模型和深度生成模型。我们的调查结果表明，噪声捕获真实数据的某些结构特性是重要的，但即使使用远离现实的过程也可以实现良好的性能。我们还发现多样性是学习良好陈述的关键财产。数据集，模型和代码可在https://mbaradad.github.io/learning_with_noise上获得。
translated by 谷歌翻译
Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (closeness) of features from positive pairs, and (2) uniformity of the induced distribution of the (normalized) features on the hypersphere. We prove that, asymptotically, the contrastive loss optimizes these properties, and analyze their positive effects on downstream tasks. Empirically, we introduce an optimizable metric to quantify each property. Extensive experiments on standard vision and language datasets confirm the strong agreement between both metrics and downstream task performance. Directly optimizing for these two metrics leads to representations with comparable or better performance at downstream tasks than contrastive learning. Project
translated by 谷歌翻译
Few-shot relation extraction (FSRE) aims at recognizing unseen relations by learning with merely a handful of annotated instances. To generalize to new relations more effectively, this paper proposes a novel pipeline for the FSRE task based on queRy-information guided Attention and adaptive Prototype fuSion, namely RAPS. Specifically, RAPS first derives the relation prototype by the query-information guided attention module, which exploits rich interactive information between the support instances and the query instances, in order to obtain more accurate initial prototype representations. Then RAPS elaborately combines the derived initial prototype with the relation information by the adaptive prototype fusion mechanism to get the integrated prototype for both train and prediction. Experiments on the benchmark dataset FewRel 1.0 show a significant improvement of our method against state-of-the-art methods.
translated by 谷歌翻译