This paper studies a majority binary neural network characterized by simple majority neurons from three binary inputs to one binary output. The dynamics is described by an autonomous difference equation and the network exhibits various binary periodic orbits. In order to analyze the network, we present simple feature quantities that evaluate period length and direct stability of periodic orbits (fixed points). Performing precise numerical analysis for low-dimensional networks, we have clarified that the networks exhibit a variety of BPOs having a long period and/or strong direct stability. Also, we have discovered multiple fixed points with the strongest direct stability. As a fundamental step to engineering applications, an FPGA-based hardware prototype is presented and typical periodic orbits are experimentally confirmed.
Graph Neural Networks (GNNs) refine embeddings by recursively aggregating information along user-item interaction edges, effectively revealing collaborative effects. Despite their empirical efficacy, GNNs struggle with data sparsity and noisy connections inherent in collaborative filtering scenarios due to their messaging mechanism. Transformer has emerged as a promising graph-structured data encoder, garnering significant attention primarily due to its global attention mechanism, which captures all-pair influences beyond neighboring nodes and thus alleviates the deficiencies of GNNs. However, directly adopting vanilla self-attention in recommendation systems does not always yield the desired results, possibly because classic ID embeddings fail to provide sufficient supervisory signals. To this end, we propose a novel topology-guided graph transformer, named ToBE, which relies solely on position encodings (PEs) that reflect the topological characteristics of nodes to measure attention scores. Furthermore, we derive two types of PEs specifically for bipartite graphs, based on random walk and Laplacian eigenmaps. Extensive experiments on six public benchmarks demonstrate that ToBE outperforms several state-of-the-art models. Further ablation studies validate the rationale and effectiveness of designed self-attention driven purely by topological PEs. The source code is available at https://github.com/liulizhi1996/ToBE .
Semantic image compression aims to reduce the amount of data transmitted by leveraging high-level semantic information for image representation and reconstruction. Considering that objects in an image vary in semantic importance, we propose a semantic-aware image compression framework that employs a diffusion model as the decoder to reconstruct visually pleasing images. The latent code generated by an autoencoder is used as a conditional input for the reverse diffusion process, where semantic importance is explicitly incorporated. To enhance the reconstruction of fine-grained details, we design a novel noise scheduling function tailored for conditional diffusion generation. Additionally, a two-stage reverse diffusion process with semantic-aware scheduling is proposed: The first stage focuses on improving the reconstruction quality of semantically critical regions, while the second stage refines the remaining areas. Experimental results demonstrate that the proposed method achieves higher perceptual quality compared to baseline approaches, along with improved pixel fidelity and semantic fidelity for semantically significant objects.
Scene understanding is a significant issue for maritime industries. Due to the large ranges involved, a model capable of localization at both short and long distances is particularly important. Currently, modern data sets have neglected the proper collection procedure and hardware to accommodate the scales of ranges at which small vessels appear. Due to other factors such as environmental challenges and data scarcity, current efficient deep learning techniques also fail to achieve high accuracies. We present High Resolution Collection Above Water (HR-CAW), a high-resolution dataset for realistic vessel segmentation, as well as addressing limitations with current data-driven approaches with a novel architecture, HC-PatchNet. Our results show that due to extreme data imbalance and diverse weather conditions, most methods for efficient high-resolution segmentation fail to converge, whereas the proposed method succeeds and achieves state-of-the-art performance.
