arXiv Machine Learning
Aug 4
Logit-Origin Centering for Singleton Test-Time Adaptation
arXiv:2608. 01074v1 Announce Type: new Abstract: Tabular data is used extensively in many real-world use cases.
Computer vision
Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
Hugging Face Trending Papers
Aug 3
Fast Object Removal Attacks on Safety-Critical Video-based Perception Systems
By leveraging data from video-based perception systems, intelligent transportation systems (ITS) support safety-critical applications that improve road safety. However, adversaries may manipulate video frames to compromise downstream perception modules, causing failures in safety-critical functions and increasing risks to vulnerable road users.
Hugging Face Trending Papers
Aug 3
DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation
Despite the remarkable progress over the past decades, accurately identifying small objects remains challenging because of their insufficient visual cues. Previous works typically attempt to construct discriminative representation of the small objects.
Hugging Face Trending Papers
Aug 3
An Accessible Solution for Deformable Image Registration Compared with Learning-Based Approaches
Deformable image registration (DIR) is a core problem in medical image analysis; but, unlike labeling decision problems such as classification and segmentation, registration is a problem class that involves stringent physical constraints. Although deep learning methods have made faster registration possible, the resulting models are often difficult to interpret compared to hand-crafted methods with explicit objectives and interpretable physical meaning.
Hugging Face Trending Papers
Aug 3
Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study
We study what happens when a single general-purpose large language model acts as the sole researcher on a long-horizon neural architecture design problem. The agent receives a scientific question, an initial hypothesis and motivation, a compute budget, and research affordances (source and experiment management, experiment tracking, literature access, and persistent memory), then autonomously proposes, implements, evaluates, and records experiments over an extended period.
Hugging Face Trending Papers
Aug 3
STC-Net: Electroluminescence-Based Solar Cell Crack Segmentation for Power Loss Estimation
Accurate crack assessment in electroluminescence (EL) images is important for photovoltaic (PV) reliability analysis, yet existing segmentation methods often fail to capture the thin, elongated, and structurally constrained nature of crack defects. This paper proposes a Solar Topology Crack Network (STC-Net) that incorporates edge priors, spectral priors, and a boundary-topology refinement module to improve crack continuity and boundary preservation.
arXiv AI
Aug 3
Dense Temporal Contrast Synthesis via Conditioned Latent Transport
arXiv:2607. 29394v1 Announce Type: cross Abstract: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is essential for breast cancer management, but reliance on gadolinium-based contrast agents (GBCAs) restricts use in contraindicated populations, prolongs scan protocols, and presents environmental toxicity concerns.
arXiv AI
Aug 3
Towards White-Box Deep Wireless Sensing
arXiv:2507. 21799v2 Announce Type: replace-cross Abstract: The empirical success of deep learning has spurred its application to the radio-frequency (RF) domain, leading to significant advances in Deep Wireless Sensing (DWS).
arXiv AI
Aug 3
A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging
arXiv:2607. 28858v1 Announce Type: cross Abstract: Automatic brain tumor segmentation from magnetic resonance imaging (MRI) has become a fundamental task in computer-assisted diagnosis, treatment planning, and disease monitoring.
arXiv AI
Aug 3
Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning
arXiv:2607. 28695v1 Announce Type: cross Abstract: Here is the plain text version optimized for arXiv's submission form.
arXiv Machine Learning
Aug 3
Lightweight Neural Networks for Affordance Segmentation: Enhancement of the Decoder Module
arXiv:2607. 29473v1 Announce Type: cross Abstract: The deployment of deep neural networks for visual affordance segmentation on wearable robots poses may prove critical, due to some conflicting aspects of the problem.
arXiv AI
Aug 3
DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation
arXiv:2607. 29337v1 Announce Type: cross Abstract: Background and Objective: Generating realistic medical images with anatomically accurate segmentation masks helps address the shortage of annotated data in medical imaging, particularly in optical coherence tomography (OCT) of mouse eyes, where manual retinal layer delineation is labour-intensive due to tiny structures and required expertise, resulting in scarce datasets.
arXiv Machine Learning
Aug 3
MoPET: Parameter-Efficient Mixture-of-Experts for Unified Medical Image Classification
arXiv:2607. 29462v1 Announce Type: cross Abstract: Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end-to-end network updates.
arXiv AI
Aug 3
TAVI-TEC: An AI-Based Tool for Procedural Planning of Transcatheter Aortic Valve Implantation
arXiv:2607. 29243v1 Announce Type: cross Abstract: Computed tomography angiography (CTA) is crucial for preprocedural TAVI planning, providing the anatomical information required for prosthesis sizing and vascular access assessment.
arXiv AI
Aug 3
Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping
arXiv:2605. 05627v2 Announce Type: replace-cross Abstract: Sustainable forest management relies on precise species composition mapping, yet traditional ground surveys are labour-intensive and geographically constrained.
arXiv Machine Learning
Aug 3
Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
arXiv Machine Learning
Aug 3
Leveraging Transfer Learning with Class-Specific Decoders for Laparoscopic Segmentation
arXiv:2607. 29509v1 Announce Type: cross Abstract: Effective multi-organ segmentation in surgical data requires learning the intricate anatomical features and alleviating the challenge of class imbalance, which results from relatively lower proportions of small and limitedly exposed structures.
arXiv Machine Learning
Aug 3
Moment kernels: a simple and scalable approach for equivariance to rotations and reflections in deep convolutional networks
arXiv:2505. 21736v2 Announce Type: replace-cross Abstract: Translation equivariance is a central reason convolutional neural networks have been successful in computer vision.
arXiv Machine Learning
Aug 3
ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research
arXiv:2506. 22174v3 Announce Type: replace-cross Abstract: The transport industry has recently shown significant interest in unmanned surface vehicles (USVs), specifically for port and inland waterway transport.
arXiv AI
Aug 3
Fast Feature Field ($\text{F}^3$): A Predictive Representation of Events
arXiv:2509. 25146v2 Announce Type: replace-cross Abstract: This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field ($\text{F}^3$).