The artificial neural networks that are used to recognize shapes typically use one or more layers of learned feature detectors that produce scalar outputs. By contrast, the computer vision community uses complicated, hand-engineered features, like SIFT [6], that produce a whole vector of outputs including an explicit representation of the pose of the feature. We show how neural networks can be used to learn features that output a whole vector of instantiation parameters and we argue that this is a much more promising way of dealing with variations in position, orientation, scale and lighting than the methods currently employed in the neural networks community. It is also more promising than the handengineered features currently used in computer vision because it provides an efficient way of adapting the features to the domain.

A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters. Active capsules at one level make predictions, via transformation matrices, for the instantiation parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active. We show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits. To achieve these results we use an iterative routing-by-agreement mechanism: A lower-level capsule prefers to send its output to higher level capsules whose activity vectors have a big scalar product with the prediction coming from the lower-level capsule.

The GLOM architecture proposed by Hinton [2021] is a recurrent neural network for parsing an image into a hierarchy of wholes and parts. When a part is ambiguous, GLOM assumes that the ambiguity can be resolved by allowing the part to make multi-modal predictions for the pose and identity of the whole to which it belongs and then using attention to similar predictions coming from other possibly ambiguous parts to settle on a common mode that is predicted by several different parts. In this study, we describe a highly simplified version of GLOM that allows us to assess the effectiveness of this way of dealing with ambiguity. Our results show that, with supervised training, GLOM is able to successfully form islands of very similar embedding vectors for all of the locations occupied by the same object and it is also robust to strong noise injections in the input and to out-of-distribution input transformations.

在这项工作中，我们调查如何实现方面，以纯粹来自数据的平台输入变换，而不会被赋予那些转换的模型。例如，卷积神经网络（CNNS）是对图像转换的等意识别，可以容易地建模的变换（通过垂直或水平地移动像素）。其他转换，例如外平面旋转，不承认一个简单的分析模型。我们提出了一种自动编码器架构，其嵌入了obeeys同时嵌入了一组任意的标准关系，例如翻译，旋转，颜色变化以及许多其他。这意味着它可以拍摄输入图像，并产生由之前未观察到的给定金额的版本（例如，相同对象的不同观点或颜色变化）。尽管延伸到许多（甚至是非几何）转换，但我们的模型在翻译标准规范的特殊情况下完全缩短了CNN。协调对深度网络的可解释性和稳健性是重要的，并且我们证明了在几个合成和实际数据集上成功重新渲染的输入图像的转换版本的结果，以及对象姿态估计的结果。

The aim of this paper is to introduce a new learning procedure for neural networks and to demonstrate that it works well enough on a few small problems to be worth further investigation. The Forward-Forward algorithm replaces the forward and backward passes of backpropagation by two forward passes, one with positive (i.e. real) data and the other with negative data which could be generated by the network itself. Each layer has its own objective function which is simply to have high goodness for positive data and low goodness for negative data. The sum of the squared activities in a layer can be used as the goodness but there are many other possibilities, including minus the sum of the squared activities. If the positive and negative passes could be separated in time, the negative passes could be done offline, which would make the learning much simpler in the positive pass and allow video to be pipelined through the network without ever storing activities or stopping to propagate derivatives.

In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters. A wide variety of filtering operations can be learned this way, including local spatial transformations, but also others like selective (de)blurring or adaptive feature extraction. Moreover, multiple such layers can be combined, e.g. in a recurrent architecture. We demonstrate the effectiveness of the dynamic filter network on the tasks of video and stereo prediction, and reach state-of-the-art performance on the moving MNIST dataset with a much smaller model. By visualizing the learned filters, we illustrate that the network has picked up flow information by only looking at unlabelled training data. This suggests that the network can be used to pretrain networks for various supervised tasks in an unsupervised way, like optical flow and depth estimation. * X. Jia and B. De Brabandere contributed equally to this work and listed in alphabetical order.

An object recognition system has been developed that uses a new class of local image features. The features are invariantto image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest-neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low-residual least-squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially-occluded images with a computation time of under 2 seconds.

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.

在过去的几年中，计算机视觉的显着进步总的来说是归因于深度学习，这是由于大量标记数据的可用性所推动的，并与GPU范式的爆炸性增长配对。在订阅这一观点的同时，本书批评了该领域中所谓的科学进步，并在基于信息的自然法则的框架内提出了对愿景的调查。具体而言，目前的作品提出了有关视觉的基本问题，这些问题尚未被理解，引导读者走上了一个由新颖挑战引起的与机器学习基础共鸣的旅程。中心论点是，要深入了解视觉计算过程，有必要超越通用机器学习算法的应用，而要专注于考虑到视觉信号的时空性质的适当学习理论。

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, returning a maximal response and orientation for every receptive field patch.H-Nets use a rich, parameter-efficient and fixed computational complexity representation, and we show that deep feature maps within the network encode complicated rotational invariants. We demonstrate that our layers are general enough to be used in conjunction with the latest architectures and techniques, such as deep supervision and batch normalization. We also achieve state-of-the-art classification on rotated-MNIST, and competitive results on other benchmark challenges.

预测性编码提供了对皮质功能的潜在统一说明 - 假设大脑的核心功能是最小化有关世界生成模型的预测错误。该理论与贝叶斯大脑框架密切相关，在过去的二十年中，在理论和认知神经科学领域都产生了重大影响。基于经验测试的预测编码的改进和扩展的理论和数学模型，以及评估其在大脑中实施的潜在生物学合理性以及该理论所做的具体神经生理学和心理学预测。尽管存在这种持久的知名度，但仍未对预测编码理论，尤其是该领域的最新发展进行全面回顾。在这里，我们提供了核心数学结构和预测编码的逻辑的全面综述，从而补充了文献中最新的教程。我们还回顾了该框架中的各种经典和最新工作，从可以实施预测性编码的神经生物学现实的微电路到预测性编码和广泛使用的错误算法的重新传播之间的紧密关系，以及对近距离的调查。预测性编码和现代机器学习技术之间的关系。

Multilayer Neural Networks trained with the backpropagation algorithm constitute the best example of a successful Gradient-Based Learning technique. Given an appropriate network architecture, Gradient-Based Learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques.Real-life document recognition systems are composed of multiple modules including eld extraction, segmentation, recognition, and language modeling. A new learning paradigm, called Graph Transformer Networks (GTN), allows such multi-module systems to be trained globally using Gradient-Based methods so as to minimize an overall performance measure.Two systems for on-line handwriting recognition are described. Experiments demonstrate the advantage of global training, and the exibility of Graph Transformer Networks.A Graph Transformer Network for reading bank check is also described. It uses Convolutional Neural Network character recognizers combined with global training techniques to provides record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network. This differentiable module can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimisation process. We show that the use of spatial transformers results in models which learn invariance to translation, scale, rotation and more generic warping, resulting in state-of-the-art performance on several benchmarks, and for a number of classes of transformations.

The current dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it also possible to learn useful features for a diverse set of visual tasks using any other form of supervision ? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in the world. Drawing inspiration from this observation, in this work we investigate if the awareness of egomotion can be used as a supervisory signal for feature learning. As opposed to the knowledge of class labels, information about egomotion is freely available to mobile agents. We show that using the same number of training images, features learnt using egomotion as supervision compare favourably to features learnt using class-label as supervision on the tasks of scene recognition, object recognition, visual odometry and keypoint matching."We move in order to see and we see in order to move"

Visual perception plays an important role in autonomous driving. One of the primary tasks is object detection and identification. Since the vision sensor is rich in color and texture information, it can quickly and accurately identify various road information. The commonly used technique is based on extracting and calculating various features of the image. The recent development of deep learning-based method has better reliability and processing speed and has a greater advantage in recognizing complex elements. For depth estimation, vision sensor is also used for ranging due to their small size and low cost. Monocular camera uses image data from a single viewpoint as input to estimate object depth. In contrast, stereo vision is based on parallax and matching feature points of different views, and the application of deep learning also further improves the accuracy. In addition, Simultaneous Location and Mapping (SLAM) can establish a model of the road environment, thus helping the vehicle perceive the surrounding environment and complete the tasks. In this paper, we introduce and compare various methods of object detection and identification, then explain the development of depth estimation and compare various methods based on monocular, stereo, and RDBG sensors, next review and compare various methods of SLAM, and finally summarize the current problems and present the future development trends of vision technologies.

The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical imaging problems that exhibit symmetries. Here we show how this principle can be extended beyond global symmetries to local gauge transformations. This enables the development of a very general class of convolutional neural networks on manifolds that depend only on the intrinsic geometry, and which includes many popular methods from equivariant and geometric deep learning.We implement gauge equivariant CNNs for signals defined on the surface of the icosahedron, which provides a reasonable approximation of the sphere. By choosing to work with this very regular manifold, we are able to implement the gauge equivariant convolution using a single conv2d call, making it a highly scalable and practical alternative to Spherical CNNs. Using this method, we demonstrate substantial improvements over previous methods on the task of segmenting omnidirectional images and global climate patterns.

We describe a model of visual processing in which feedback connections from a higher-to a lowerorder visual cortical area carry predictions of lower-level neural activities, whereas the feedforward connections carry the residual errors between the predictions and the actual lower-level activities. When exposed to natural images, a hierarchical network of model neurons implementing such a model developed simple-cell-like receptive fields. A subset of neurons responsible for carrying the residual errors showed endstopping and other extra-classical receptive-field effects. These results suggest that rather than being exclusively feedforward phenomena, nonclassical surround effects in the visual cortex may also result from cortico-cortical feedback as a consequence of the visual system using an efficient hierarchical strategy for encoding natural images.

It is possible to combine multiple latent-variable models of the same data by multiplying their probability distributions together and then renormalizing. This way of combining individual "expert" models makes it hard to generate samples from the combined model but easy to infer the values of the latent variables of each expert, because the combination rule ensures that the latent variables of different experts are conditionally independent when given the data. A product of experts (PoE) is therefore an interesting candidate for a perceptual system in which rapid inference is vital and generation is unnecessary. Training a PoE by maximizing the likelihood of the data is difficult because it is hard even to approximate the derivatives of the renormalization term in the combination rule. Fortunately, a PoE can be trained using a different objective function called "contrastive divergence" whose derivatives with regard to the parameters can be approximated accurately and efficiently. Examples are presented of contrastive divergence learning using several types of expert on several types of data.

机器学习的最近进步已经创造了利用一类基于坐标的神经网络来解决视觉计算问题的兴趣，该基于坐标的神经网络在空间和时间跨空间和时间的场景或对象的物理属性。我们称之为神经领域的这些方法已经看到在3D形状和图像的合成中成功应用，人体的动画，3D重建和姿势估计。然而，由于在短时间内的快速进展，许多论文存在，但尚未出现全面的审查和制定问题。在本报告中，我们通过提供上下文，数学接地和对神经领域的文学进行广泛综述来解决这一限制。本报告涉及两种维度的研究。在第一部分中，我们通过识别神经字段方法的公共组件，包括不同的表示，架构，前向映射和泛化方法来专注于神经字段的技术。在第二部分中，我们专注于神经领域的应用在视觉计算中的不同问题，超越（例如，机器人，音频）。我们的评论显示了历史上和当前化身的视觉计算中已覆盖的主题的广度，展示了神经字段方法所带来的提高的质量，灵活性和能力。最后，我们展示了一个伴随着贡献本综述的生活版本，可以由社区不断更新。

面部特征跟踪是成像跳芭式（BCG）的关键组成部分，其中需要精确定量面部关键点的位移，以获得良好的心率估计。皮肤特征跟踪能够在帕金森病中基于视频的电机降解量化。传统的计算机视觉算法包括刻度不变特征变换（SIFT），加速强大的功能（冲浪）和LUCAS-KANADE方法（LK）。这些长期代表了最先进的效率和准确性，但是当存在常见的变形时，如图所示，如图所示，如此。在过去的五年中，深度卷积神经网络对大多数计算机视觉任务的传统方法表现优于传统的传统方法。我们提出了一种用于特征跟踪的管道，其应用卷积堆积的AutoEncoder，以将图像中最相似的裁剪标识到包含感兴趣的特征的参考裁剪。 AutoEncoder学会将图像作物代表到特定于对象类别的深度特征编码。我们在面部图像上培训AutoEncoder，并验证其在手动标记的脸部和手视频中通常验证其跟踪皮肤功能的能力。独特的皮肤特征（痣）的跟踪误差是如此之小，因为我们不能排除他们基于$ \ chi ^ 2 $ -test的手动标签。对于0.6-4.2像素的平均误差，我们的方法在所有情况下都表现出了其他方法。更重要的是，我们的方法是唯一一个不分歧的方法。我们得出的结论是，我们的方法为特征跟踪，特征匹配和图像配准比传统算法创建更好的特征描述符。