Related papers: IBCapsNet: Information Bottleneck Capsule Network …

We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. The new mechanism 1) designs routing via inverted dot-product…

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias…

We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet). Specifically, we…

The paper investigates the performance of state-of-the-art low-parameter deep neural networks for computer vision, focusing on bottleneck architectures and their behavior using superlinear activation functions. We address interference in…

Artificial sound event detection (SED) has the aim to mimic the human ability to perceive and understand what is happening in the surroundings. Nowadays, Deep Learning offers valuable techniques for this goal such as Convolutional Neural…

Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now playing a pivotal role in various aspect of society. The goal in statistical learning is to use data to obtain simple algorithms for predicting a…

Maintaining efficient semantic representations of the environment is a major challenge both for humans and for machines. While human languages represent useful solutions to this problem, it is not yet clear what computational principle…

In this paper, we propose Binarized Change Detection (BiCD), the first binary neural network (BNN) designed specifically for change detection. Conventional network binarization approaches, which directly quantize both weights and…

Expert systems often operate in domains characterized by class-imbalanced tabular data, where detecting rare but critical instances is essential for safety and reliability. While conventional approaches, such as cost-sensitive learning,…

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models that would provide…

Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated. To close this gap, we first conduct an empirical…

Building on recent work on capsule networks, we propose a new, general-purpose form of "routing by agreement" that activates output capsules in a layer as a function of their net benefit to use and net cost to ignore input capsules from…

Three-dimensional generative models increasingly drive structure-based drug discovery, yet it remains constrained by the scarce publicly available protein-ligand complexes. Under such data scarcity, almost all existing pipelines struggle to…

High-fidelity binaural audio synthesis is crucial for immersive listening, but existing methods require extensive computational resources, limiting their edge-device application. To address this, we propose the Lightweight Implicit Neural…

Learning on high-order correlation has shown superiority in data representation learning, where hypergraph has been widely used in recent decades. The performance of hypergraph-based representation learning methods, such as hypergraph…

Image classification has become one of the main tasks in the field of computer vision technologies. In this context, a recent algorithm called CapsNet that implements an approach based on activity vectors and dynamic routing between…

Decisions of complex language understanding models can be rationalized by limiting their inputs to a relevant subsequence of the original text. A rationale should be as concise as possible without significantly degrading task performance,…

In the last few years, compression of deep neural networks has become an important strand of machine learning and computer vision research. Deep models require sizeable computational complexity and storage, when used for instance for Human…

Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider…

Contrastive learning (CL) has shown great power in self-supervised learning due to its ability to capture insight correlations among large-scale data. Current CL models are biased to learn only the ability to discriminate positive and…