Capsule networks (CapsNets) were introduced to address convolutional neural networks limitations, learning object-centric representations that are more robust, pose-aware, and interpretable. They organize neurons into groups called capsules, where each capsule encodes the instantiation parameters of an object or one of its parts. Moreover, a routing algorithm connects capsules in different layers, thereby capturing hierarchical part-whole relationships in the data. This thesis investigates the intriguing aspects of CapsNets and focuses on three key questions to unlock their full potential. First, we explore the effectiveness of the routing algorithm, particularly in small-sized networks. We propose a novel method that anneals the number of routing iterations during training, enhancing performance in architectures with fewer parameters. Secondly, we investigate methods to extract more effective first-layer capsules, also known as primary capsules. By exploiting pruned backbones, we aim to improve computational efficiency by reducing the number of capsules while achieving high generalization. This approach reduces CapsNets memory requirements and computational effort. Third, we explore part-relationship learning in CapsNets. Through extensive research, we demonstrate that capsules with low entropy can extract more concise and discriminative part-whole relationships compared to traditional capsule networks, even with reasonable network sizes. Lastly, we showcase how CapsNets can be utilized in real-world applications, including autonomous localization of unmanned aerial vehicles, quaternion-based rotations prediction in synthetic datasets, and lung nodule segmentation in biomedical imaging. The findings presented in this thesis contribute to a deeper understanding of CapsNets and highlight their potential to address complex computer vision challenges.

Due to the highly dynamic changes in wireless network topologies, efficiently obtaining network status information and flexibly forwarding data to improve communication quality of service are important challenges. This article introduces an intelligent routing algorithm (DRL-PPONSA) based on proximal policy optimization deep reinforcement learning with network situational awareness under a software-defined wireless networking architecture. First, a specific data plane is designed for network topology construction and data forwarding. The control plane collects network traffic information, sends flow tables, and uses a GCN-GRU prediction mechanism to perceive future traffic change trends to achieve network situational awareness. Second, a DRL-based data forwarding mechanism is designed in the knowledge plane. The predicted network traffic matrix and topology information matrix are treated as the environment for DRL agents, while next-hop adjacent nodes are treated as executable actions. Accordingly, action selection strategies are designed for different network conditions to achieve more intelligent, flexible, and efficient routing control. The reward function is designed using network link information and various reward and penalty mechanisms. Additionally, importance sampling and gradient clipping techniques are employed during gradient updating to enhance convergence speed and stability. Experimental results show that DRL-PPONSA outperforms traditional routing methods in network throughput, delay, packet loss rate, and wireless node distance. Compared to value-function-based Dueling DQN routing, the convergence speed is significantly improved, and the convergence effect is more stable. Simultaneously, its consumption of hardware storage space is reduced, and efficient routing decisions can be made in real-time using the current network state information.

Affordance detection from visual input is a fundamental step in autonomous robotic manipulation. Existing solutions to the problem of affordance detection rely on convolutional neural networks. However, these networks do not consider the spatial arrangement of the input data and miss parts-to-whole relationships. Therefore, they fall short when confronted with novel, previously unseen object instances or new viewpoints. One solution to overcome such limitations can be to resort to capsule networks. In this paper, we introduce the first affordance detection network based on dynamic tree-structured capsules for sparse 3D point clouds. We show that our capsule-based network outperforms current state-of-the-art models on viewpoint invariance and parts-segmentation of new object instances through a novel dataset we only used for evaluation and it is publicly available from github.com/gipfelen/DTCG-Net. In the experimental evaluation we will show that our algorithm is superior to current affordance detection methods when faced with grasping previously unseen objects thanks to our Capsule Network enforcing a parts-to-whole representation.

Sparse expert models are a thirty-year old concept re-emerging as a popular architecture in deep learning. This class of architecture encompasses Mixture-of-Experts, Switch Transformers, Routing Networks, BASE layers, and others, all with the unifying idea that each example is acted on by a subset of the parameters. By doing so, the degree of sparsity decouples the parameter count from the compute per example allowing for extremely large, but efficient models. The resulting models have demonstrated significant improvements across diverse domains such as natural language processing, computer vision, and speech recognition. We review the concept of sparse expert models, provide a basic description of the common algorithms, contextualize the advances in the deep learning era, and conclude by highlighting areas for future work. Remarkable advances in machine learning - especially in natural language - have been achieved by increasing the computational budget, training data, and model size. However, state-of-the-art models now require thousands of specialized, interconnected accelerators for weeks or months at a time. These models are therefore expensive to produce and incur high energy costs (Patterson et al., 2021). Therefore, as the scale of machine learning systems has increased, the field has sought more efficient training and serving paradigms. Sparse expert models have risen as a promising solution. A dense model (left) sends both input tokens to the same feed-forward network parameters (FFN). In this diagram, each model uses a similar amount of computation, but the sparse model has more unique parameters. Note while this figure showcases a specific and common approach of sparse feed-forward network layers in a Transformer (Vaswani et al., 2017), the technique is more general. Sparse expert models, of which, Mixture-of-Experts (MoE) is the most popular variant, are neural networks where a set of the parameters are partitioned into "experts", each with a unique weight. As a result, each example only interacts with a subset of the network parameters, contrasting the usual approach where the entire network is used for each input. Because only a fraction of the experts are used for each example, the amount of computation may remain small relative to the total model size. Many modern sparse expert models draw inspiration from Shazeer et al. (2017), which trained the largest model at the time and achieved state-of-the-art language modeling and translation results.

Welcome to the 4th issue of the Papers with Code newsletter. Self-attention continues to be adopted to build deep learning architectures that address computer vision problems like instance segmentation and object detection. One recent example is Vision Transformer (ViT) proposed by Dosovitskiy et al. Despite being promising for vision tasks, these large models can show computational inefficiencies and inferior performance (compared to established vision architectures). This leaves room for improvements.

Program comprehension is a fundamental task in software development and maintenance processes. Software developers often need to understand a large amount of existing code before they can develop new features or fix bugs in existing programs. Being able to process programming language code automatically and provide summaries of code functionality accurately can significantly help developers to reduce time spent in code navigation and understanding, and thus increase productivity. Different from natural language articles, source code in programming languages often follows rigid syntactical structures and there can exist dependencies among code elements that are located far away from each other through complex control flows and data flows. Existing studies on tree-based convolutional neural networks (TBCNN) and gated graph neural networks (GGNN) are not able to capture essential semantic dependencies among code elements accurately. In this paper, we propose novel tree-based capsule networks (TreeCaps) and relevant techniques for processing program code in an automated way that encodes code syntactical structures and captures code dependencies more accurately. Based on evaluation on programs written in different programming languages, we show that our TreeCaps-based approach can outperform other approaches in classifying the functionalities of many programs.

The capsules of Capsule Networks are collections of neurons that represent an object or part of an object in a parse tree. The output vector of a capsule encodes the so called instantiation parameters of this object (e.g. position, size, or orientation). The routing-by-agreement algorithm routes output vectors from lower level capsules to upper level capsules. This iterative algorithm selects the most appropriate parent capsule so that the active capsules in the network represent nodes in a parse tree. This parse tree represents the hierarchical composition of objects out of smaller and smaller components. In this paper, we will show experimentally that the routing-by-agreement algorithm does not ensure the emergence of a parse tree in the network. To ensure that all active capsules form a parse tree, we introduce a new routing algorithm called dynamic deep routing. We show that this routing algorithm allows the training of deeper capsule networks and is also more robust to white box adversarial attacks than the original routing algorithm.

Text classification is a challenging problem which aims to identify the category of texts. Recently, Capsule Networks (CapsNets) are proposed for image classification. It has been shown that CapsNets have several advantages over Convolutional Neural Networks (CNNs), while, their validity in the domain of text has less been explored. An effective method named deep compositional code learning has been proposed lately. This method can save many parameters about word embeddings without any significant sacrifices in performance. In this paper, we introduce the Compositional Coding (CC) mechanism between capsules, and we propose a new routing algorithm, which is based on k-means clustering theory. Experiments conducted on eight challenging text classification datasets show the proposed method achieves competitive accuracy compared to the state-of-the-art approach with significantly fewer parameters.