We introduce Active Predictive Coding Networks (APCNs), a new class of neural networks that solve a major problem posed by Hinton and others in the fields of artificial intelligence and brain modeling: how can neural networks learn intrinsic reference frames for objects and parse visual scenes into part-whole hierarchies by dynamically allocating nodes in a parse tree? APCNs address this problem by using a novel combination of ideas: (1) hypernetworks are used for dynamically generating recurrent neural networks that predict parts and their locations within intrinsic reference frames conditioned on higher object-level embedding vectors, and (2) reinforcement learning is used in conjunction with backpropagation for end-to-end learning of model parameters. The APCN architecture lends itself naturally to multi-level hierarchical learning and is closely related to predictive coding models of cortical function. Using the MNIST, Fashion-MNIST and Omniglot datasets, we demonstrate that APCNs can (a) learn to parse images into part-whole hierarchies, (b) learn compositional representations, and (c) transfer their knowledge to unseen classes of objects. With their ability to dynamically generate parse trees with part locations for objects, APCNs offer a new framework for explainable AI that leverages advances in deep learning while retaining interpretability and compositionality.
This paper presents a model architecture for encoding the representations of part-whole hierarchies in images in form of a graph. The idea is to divide the image into patches of different levels and then treat all of these patches as nodes for a fully connected graph. A dynamic feature extraction module is used to extract feature representations from these patches in each graph iteration. This enables us to learn a rich graph representation of the image that encompasses the inherent part-whole hierarchical information. Utilizing proper self-supervised training techniques, such a model can be t…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；University of British Columbia（不列颠哥伦比亚大学）
Strong evidence suggests that humans perceive the 3D world by parsing visual scenes and objects into part-whole hierarchies. Although deep neural networks have the capability of learning powerful multi-level representations, they can not explicitly model part-whole hierarchies, which limits their expressiveness and interpretability in processing 3D vision data such as point clouds. To this end, we propose an encoder-decoder style latent variable model that explicitly learns the part-whole hierarchies for the multi-level point cloud segmentation. Specifically, the encoder takes a point cloud as…
Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision
Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）
Google Research（谷歌研究院）；The Vector Institute（向量研究所）；University of Toronto（多伦多大学）
This paper does not describe a working system. Instead, it presents a single idea about representation which allows advances made by several different groups to be combined into an imaginary system called GLOM. The advances include transformers, neural fields, contrastive representation learning, distillation and capsules. GLOM answers the question: How can a neural network with a fixed architecture parse an image into a part-whole hierarchy which has a different structure for each image? The idea is simply to use islands of identical vectors to represent the nodes in the parse tree. If GLOM c…
Beijing University of Posts and Telecommunications（北京邮电大学）
Classical communication paradigms focus on accurately transmitting bits over a noisy channel, and Shannon theory provides a fundamental theoretical limit on the rate of reliable communications. In this approach, bits are treated equally, and the communication system is oblivious to what meaning these bits convey or how they would be used. Future communications towards intelligence and conciseness will predictably play a dominant role, and the proliferation of connected intelligent agents requires a radical rethinking of coded transmission paradigm to support the new communication morphology on…
Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. When it comes to critical applications as autonomous driving, security and safety, medicine and health, the lack of interpretability of the network behavior tends to induce skepticism and…
University of Oxford（牛津大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Human vision is able to capture the part-whole hierarchical information from the entire scene. This paper presents the Visual Parser (ViP) that explicitly constructs such a hierarchy with transformers. ViP divides visual representations into two levels, the part level and the whole level. Information of each part represents a combination of several independent vectors within the whole. To model the representations of the two levels, we first encode the information from the whole into part vectors through an attention mechanism, then decode the global information within the part vectors back in…
DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
University of Science and Technology of China (USTC)（中国科学技术大学）；Stanford University（斯坦福大学）；Suzhou Institute for Advanced Research, USTC（中国科学技术大学苏州高等研究院）；Tongji University（同济大学）
Harbin Engineering University（哈尔滨工程大学）；University of California, Los Angeles（加州大学洛杉矶分校）
We introduce an explainable generative model by applying sparse operation on the feature maps of the generator network. Meaningful hierarchical representations are obtained using the proposed generative model with sparse activations. The convolutional kernels from the bottom layer to the top layer of the generator network can learn primitives such as edges and colors, object parts, and whole objects layer by layer. From the perspective of the generator network, we propose a method for inducing both sparse coding and the AND-OR grammar for images. Experiments show that our method is capable of …
Harbin Institute of Technology（哈尔滨工业大学）；Huawei（华为）
Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split…
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…
We describe a method for fast approximation of sparse coding. The input space is subdivided by a binary decision tree, and we simultaneously learn a dictionary and assignment of allowed dictionary elements for each leaf of the tree. We store a lookup table with the assignments and the pseudoinverses for each node, allowing for very fast inference. We give an algorithm for learning the tree, the dictionary and the dictionary element assignment, and In the process of describing this algorithm, we discuss the more general problem of learning the groups in group structured sparse modelling. We sho…
Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（矢量人工智能研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席项目）
A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new challenges stemming from occlusions not depicted in the image. Prior works try to overcome these by inferring from multiple views or rely on scarce CAD models and category-specific priors which hinder scaling to novel settings. In this work, we explore single-view 3D reconstruction by learning generalizable representations inspired by advances in self-supervi…
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…
Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots. In this paper, we present a flexible and high-performance 3D detection framework, named MPPNet, for 3D temporal object detection with point cloud sequences. We propose a novel three-hierarchy framework with proxy points for multi-frame feature encoding and interactions to achieve better detection. The three hierarchies conduct per-frame feature encoding, short-clip feature fusion, and whole-sequence feature aggregation, respectively. To enable processing long-sequence poi…
Nanjing University of Posts and Telecommunications（南京邮电大学）；Nanjing University of Science and Technology（南京理工大学）；Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education（高维信息智能感知与系统教育部重点实验室）
In this paper, we propose an easily trained yet powerful representation learning approach with performance highly competitive to deep neural networks in a digital pathology image segmentation task. The method, called sparse coding driven deep decision tree ensembles that we abbreviate as ScD2TE, provides a new perspective on representation learning. We explore the possibility of stacking several layers based on non-differentiable pairwise modules and generate a densely concatenated architecture holding the characteristics of feature map reuse and end-to-end dense learning. Under this architect…
Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Local and global patterns of an object are closely related. Although each part of an object is incomplete, the underlying attributes about the object are shared among all parts, which makes reasoning the whole object from a single part possible. We hypothesize that a powerful representation of a 3D object should model the attributes that are shared between parts and the whole object, and distinguishable from other objects. Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the…
College of Computer Science, Sichuan University（四川大学计算机学院）；Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China and the School of Electronics Engineering and Computer Science, Peking University, China（北京大学电子工程与计算机科学学院）；Shanghai First-imaging Information Technology co. LTD（上海第一影像信息技术有限公司）；school of Mathematics and Computer Science, Gannan Normal University（赣南师范大学数学与计算机科学学院）；Rutgers, the State University of New Jersey（罗格斯大学（新泽西州立大学））；Department of Radiology, West China Hospital of Sichuan University（四川大学华西医院放射科）
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explor…
