The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for self-supervised representation learning on videos. This learns a dense encoding of spatio-temporal blocks by recurrently predicting future representations; Second, we propose a curriculum training scheme to predict further into the future with progressively less temporal context. This encourages the model to only encode slowly varying spatial-temporal signals, therefore leading to semantic representations; Third, we evaluate the approach by first training the DPC model on the Kinetics-400 dataset with self-supervised learning, and then finetuning the representation on a downstream task, i.e. action recognition. With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101(75.7% top1 acc) and HMDB51(35.7% top1 acc), outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.
The objective of this paper is self-supervised learning from video, in particular for representations for action recognition. We make the following contributions: (i) We propose a new architecture and learning framework Memory-augmented Dense Predictive Coding (MemDPC) for the task. It is trained with a predictive attention mechanism over the set of compressed memories, such that any future states can always be constructed by a convex combination of the condense representations, allowing to make multiple hypotheses efficiently. (ii) We investigate visual-only self-supervised video representati…
Singapore University of Technology and Design（新加坡科技设计大学）；Goethe University of Frankfurt am Main（法兰克福大学）
Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is key to achieve high accuracy performance on this task. Most of the state-of-the-art methods rely on RGB frames for extracting the semantics and pre-computed optical flow fields as a motion cue. Then, both are combined using deep neural networks. Yet, it has been argued that such models are not able to leverage the motion information extracted from the optical flow, but instead the optical flow allows for better recogn…
Okinawa Institute of Science and Technology (OIST)（冲绳科学技术大学院大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
The current paper presents how a predictive coding type deep recurrent neural networks can generate vision-based goal-directed plans based on prior learning experience by examining experiment results using a real arm robot. The proposed deep recurrent neural network learns to predict visuo-proprioceptive sequences by extracting an adequate predictive model from various visuomotor experiences related to object-directed behaviors. The predictive model was developed in terms of mapping from intention state space to expected visuo-proprioceptive sequences space through iterative learning. Our arm …
School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
A novel coding strategy for block-based compressive sens-ing named spatially directional predictive coding (SDPC) is proposed, which efficiently utilizes the intrinsic spatial cor-relation of natural images. At the encoder, for each block of compressive sensing (CS) measurements, the optimal pre-diction is selected from a set of prediction candidates that are generated by four designed directional predictive modes. Then, the resulting residual is processed by scalar quantiza-tion (SQ). At the decoder, the same prediction is added onto the de-quantized residuals to produce the quantized CS meas…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
The current paper presents a novel recurrent neural network model, the predictive multiple spatio-temporal scales RNN (P-MSTRNN), which can generate as well as recognize dynamic visual patterns in the predictive coding framework. The model is characterized by multiple spatio-temporal scales imposed on neural unit dynamics through which an adequate spatio-temporal hierarchy develops via learning from exemplars. The model was evaluated by conducting an experiment of learning a set of whole body human movement patterns which was generated by following a hierarchically defined movement syntax. The…
DMPCN: Dynamic Modulated Predictive Coding Network with Hybrid Feedback Representations
Department of Artificial Intelligence and Robotics（人工智能与机器人系）；Sejong University（世宗大学）；AI Lab（人工智能实验室）；MetaSyntec（MetaSyntec公司）；School of Computer Science（计算机科学学院）；Peking University（北京大学）
Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural networks, PCN includes both feedback connections, which carry top-down predictions, and feedforward connections, which carry bottom-up errors of prediction. Feedback and feedforward connections enable adjacent layers to interact locally and recurrently to refine representations towards minimization of layer-wise prediction errors. When unfolded over time, the recur…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Facebook AI Research（脸书人工智能研究院）
We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of images gathered by an agent as it moves about in 3D environments. We learn these representations via a zone prediction task, where we intelligently mask out portions of an agent's trajectory and predict them from the unmasked portions, conditioned on the agent's camera poses. By learning such representations on a collection of videos, we demonstrate successful…
Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedback connections from a higher layer carry the prediction of its lower-layer representation; feedforward connections carry the prediction errors to its higher-layer. Given image input, PCN runs recursive cycles of bottom-up and top-down computation to update its internal representations and reduce the difference between bottom-up input and top-down prediction at every layer. After…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Okinawa Institute of Science and Technology (OIST)（冲绳科学技术大学院大学）
The current paper proposes a novel predictive coding type neural network model, the predictive multiple spatio-temporal scales recurrent neural network (P-MSTRNN). The P-MSTRNN learns to predict visually perceived human whole-body cyclic movement patterns by exploiting multiscale spatio-temporal constraints imposed on network dynamics by using differently sized receptive fields as well as different time constant values for each layer. After learning, the network becomes able to proactively imitate target movement patterns by inferring or recognizing corresponding intentions by means of the reg…
Rochester Institute of Technology（罗切斯特理工学院）；University of South Florida（南佛罗里达大学）
In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible neurobiologically-motivated algorithm that progressively refines latent state feature maps in order to dynamically form a more accurate internal representation/reconstruction model of natural images. The performance of the resulting sensory processing system is evaluated on complex datasets such as Color-MNIST, CIFAR-10, and Street House View Numbers (SVHN). We study the eff…
Bayesian predictive coding is a putative neuromorphic method for acquiring higher-level neural representations to account for sensory input. Although originating in the neuroscience community, there are also efforts in the machine learning community to study these models. This paper reviews some of the more well known models. Our review analyzes module connectivity and patterns of information transfer, seeking to find general principles used across the models. We also survey some recent attempts to cast these models within a deep learning framework. A defining feature of Bayesian predictive co…
University of Potsdam（波茨坦大学）；Otto von Guericke University（奥托·冯·格里克大学）
PredNet, a deep predictive coding network developed by Lotter et al., combines a biologically inspired architecture based on the propagation of prediction error with self-supervised representation learning in video. While the architecture has drawn a lot of attention and various extensions of the model exist, there is a lack of a critical analysis. We fill in the gap by evaluating PredNet both as an implementation of the predictive coding theory and as a self-supervised video prediction model using a challenging video action classification dataset. We design an extended model to test if condit…
South China University of Technology（华南理工大学）；The Hong Kong Polytechnic University（香港理工大学）
Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with the problems. Predictive coding provides an interesting and reliable computational framework, which will be combined with other theories such as the cerebral cortex at different level oscillates at different frequencies, to design an e…
Aalto University（阿尔托大学）；University of Amsterdam（阿姆斯特丹大学）；Centrum Wiskunde & Informatica（数学与计算机科学研究中心）；Bristol Robotics Laboratory（布里斯托尔机器人实验室）
Extracting and binding salient information from different sensory modalities to determine common features in the environment is a significant challenge in robotics. Here we present MuPNet (Multi-modal Predictive Coding Network), a biologically plausible network architecture for extracting joint latent features from visuo-tactile sensory data gathered from a biomimetic mobile robot. In this study we evaluate MuPNet applied to place recognition as a simulated biomimetic robot platform explores visually aliased environments. The F1 scores demonstrate that its performance over prior hand-crafted s…
DeepMind；University of California, Berkeley（加利福尼亚大学伯克利分校）
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification wit…
The Edmond and Lily Safra Center for Brain Sciences（埃德蒙和莉莉·萨夫拉脑科学中心）
Video prediction models often combine three components: an encoder from pixel space to a small latent space, a latent space prediction model, and a generative model back to pixel space. However, the large and unpredictable pixel space makes training such models difficult, requiring many training examples. We argue that finding a predictive latent variable and using it to evaluate the consistency of a future image enables data-efficient predictions because it precludes the necessity of a generative model training. To demonstrate it, we created sequence completion intelligence tests in which the…
Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly popular, given the impressive results they have achieved in self-supervised representation learning settings. However, while most existing contrastive anomaly detection and segmentation approaches have been applied to images, none of them can use the contrastive losses directly for both anomaly detection and segmentation. In this paper, we close this gap by maki…
CerCo CNRS（法国国家科学研究中心大脑与认知研究中心）；Université de Toulouse（图卢兹大学）；IRIT CNRS（法国国家科学研究中心图卢兹计算机科学研究所）；ANITI（图卢兹人工智能跨学科研究所）
Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks. We take inspiration from a popular framework in neuroscience: 'predictive coding'. At each layer of the hierarchical model, generative feedback 'predicts' (i.e., reconstructs) the pattern of activity in the previous layer. The reconstruction errors are used to iteratively update the network's representat…
University of Science and Technology of China（中国科学技术大学）
Objective quality assessment of stereoscopic omnidirectional images is a challenging problem since it is influenced by multiple aspects such as projection deformation, field of view (FoV) range, binocular vision, visual comfort, etc. Existing studies show that classic 2D or 3D image quality assessment (IQA) metrics are not able to perform well for stereoscopic omnidirectional images. However, very few research works have focused on evaluating the perceptual visual quality of omnidirectional images, especially for stereoscopic omnidirectional images. In this paper, based on the predictive codin…
CerCo, CNRS（法国国家科学研究中心 脑与认知研究中心）；IRIT, CNRS（法国国家科学研究中心 图卢兹信息学研究所）；ANITI, Université de Toulouse（图卢兹大学 人工智能与自然智能研究所）
Brain-inspired machine learning is gaining increasing consideration, particularly in computer vision. Several studies investigated the inclusion of top-down feedback connections in convolutional networks; however, it remains unclear how and when these connections are functionally helpful. Here we address this question in the context of object recognition under noisy conditions. We consider deep convolutional networks (CNNs) as models of feed-forward visual processing and implement Predictive Coding (PC) dynamics through feedback connections (predictive feedback) trained for reconstruction or c…
University of Dundee（邓迪大学）；Ninewells Hospital and Medical School（奈恩韦尔斯医院与医学院）
Digital pathology tasks have benefited greatly from modern deep learning algorithms. However, their need for large quantities of annotated data has been identified as a key challenge. This need for data can be countered by using unsupervised learning in situations where data are abundant but access to annotations is limited. Feature representations learned from unannotated data using contrastive predictive coding (CPC) have been shown to enable classifiers to obtain state of the art performance from relatively small amounts of annotated computer vision data. We present a modification to the CP…
Predictive coding, currently a highly influential theory in neuroscience, has not been widely adopted in machine learning yet. In this work, we transform the seminal model of Rao and Ballard (1999) into a modern deep learning framework while remaining maximally faithful to the original schema. The resulting network we propose (PreCNet) is tested on a widely used next frame video prediction benchmark, which consists of images from an urban environment recorded from a car-mounted camera, and achieves state-of-the-art performance. Performance on all measures (MSE, PSNR, SSIM) was further improved…
Naval Surface Warfare Center（海军水面作战中心）；US Naval Sea Systems Command（美国海军海上系统司令部）；University of Florida（佛罗里达大学）
Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse, invariant features. However, this inference is a major computational bottleneck. It severely limits the network depth due to learning stagnation. Here, we prove why this bottleneck occurs. We then propose a new forward-inference strategy based on accelerated proximal gradients. This st…
The quality of data representation in deep learning methods is directly related to the prior model imposed on the representations; however, generally used fixed priors are not capable of adjusting to the context in the data. To address this issue, we propose deep predictive coding networks, a hierarchical generative model that empirically alters priors on the latent representations in a dynamic and context-sensitive manner. This model captures the temporal dependencies in time-varying signals and uses top-down information to modulate the representation in lower layers. The centerpiece of our m…
