Related papers: Sort & Slice: A Simple and Superior Alternative to…

Graph convolutional networks (GCNs) are becoming increasingly popular as they can process a wide variety of data formats that prior deep neural networks cannot easily support. One key challenge in designing hardware accelerators for GCNs is…

Recently, the transductive graph-based methods have achieved great success in the few-shot classification task. However, most existing methods ignore exploring the class-level knowledge that can be easily learned by humans from just a…

A simple and fast analysis method to sort large data sets into groups with shared distinguishing characteristics is described, and applied to single molecular break junction conductance versus electrode displacement data. The method, based…

An efficient integer factorization algorithm would reduce the security of all variants of the RSA cryptographic scheme to zero. Despite the passage of years, no method for efficiently factoring large semiprime numbers in a classical…

Semisort is a fundamental algorithmic primitive widely used in the design and analysis of efficient parallel algorithms. It takes input as an array of records and a function extracting a \emph{key} per record, and reorders them so that…

The slice decomposition is a bijective method for enumerating planar maps (graphs embedded in the sphere) with control over face degrees. In this paper, we extend the slice decomposition to the richer setting of hypermaps, naturally…

Based on PixelHop and PixelHop++, which are recently developed using the successive subspace learning (SSL) framework, we propose an enhanced solution for object classification, called E-PixelHop, in this work. E-PixelHop consists of the…

Incremental few-shot semantic segmentation (IFSS) targets at incrementally expanding model's capacity to segment new class of images supervised by only a few samples. However, features learned on old classes could significantly drift,…

The growing popularity of robotic minimally invasive surgeries has made deep learning-based surgical training a key area of research. A thorough understanding of the surgical scene components is crucial, which semantic segmentation models…

Learning-based hashing algorithms are ``hot topics" because they can greatly increase the scale at which existing methods operate. In this paper, we propose a new learning-based hashing method called ``fast supervised discrete hashing"…

The observation, design and analysis of mesh-like networks in bionics, polymer physics and biological systems has brought forward an extensive catalog of fascinating structures of which a subgroup share a particular, yet critically under…

Functional groups and moieties are chemical descriptors of biomolecules that can be used to interpret their properties and functions, leading to the understanding of chemical or biological mechanisms. These chemical building blocks, or…

Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Subgraph classification has applications such as predicting the cellular…

We present a simple but effective method for automatic latent fingerprint segmentation, called SegFinNet. SegFinNet takes a latent image as an input and outputs a binary mask highlighting the friction ridge pattern. Our algorithm combines…

Hypergraphs allow modeling problems with multi-way high-order relationships. However, the computational cost of most existing hypergraph-based algorithms can be heavily dependent upon the input hypergraph sizes. To address the…

Accurate segmentation of medical images is essential for diagnosis and treatment of diseases. These problems are solved by highly complex models, such as deep networks (DN), requiring a large amount of labeled data for training. Thereby,…

Traditional molecular string representations, such as SMILES, often pose challenges for AI-driven molecular design due to their non-sequential depiction of molecular substructures. To address this issue, we introduce Sequential…

Supervised fine-tuning (SFT) followed by reinforcement learning (RL) has become a standard post-training paradigm for large language models. This paradigm provides a cold-start for RL exploration, avoiding the inefficiency of pure RL where…

Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly based on insufficient hand-crafted rules that only partially…

Hashing methods have been widely used for efficient similarity retrieval on large scale image database. Traditional hashing methods learn hash functions to generate binary codes from hand-crafted features, which achieve limited accuracy…