Training boost: a new image representation for enhanced edge detection in neural networks

Long-sequence modeling for sparse-view computed tomography reconstruction

This work integrates selective State Space Model mechanisms from Mamba and three approximate self-attention methods, including Longformer, LongNet, and Nyströmformer, into a regularization-based reconstruction network that enables efficient modeling of long-range dependencies using modern sequence-processing architectu...

P-PatchDiff: Progressive Patch Diffusion Models for Low-Light Image Enhancement

Recent advancements in low-light image enhancement have leveraged diffusion models for their strong ability to generate perceptually realistic, detailed images. Patch diffusion models further offer a promising solution to size-agnostic image restoration while improving efficiency. However, existing methods typically re...

ACPNet: adaptive concept-prototype network for interpretable fine-grained image classification

Edge deployment of YOLOv12 and YOLOv26 instance segmentation for real-time steel surface defect inspection

Real-time automated steel surface inspection on the production line is challenging. Defect masks must be produced at the camera’s acquisition rate and within the power envelope of an embedded GPU. This paper evaluates two contrasting YOLO architectures, the attention-centric YOLOv12 and the convolution-centric YOLOv26,...

SM2-LF: semi-supervised oriented object detection in remote sensing via adaptive pseudo-label optimization

Atwood-weighted Normalized Mutual Information (ANMI): a physics-inspired metric for image classification evaluation

Normalized Mutual Information (NMI) is a widely used metric for evaluating image classification and clustering. However, standard NMI often yields over-optimistic results when there is a significant discrepancy in cluster density, such as in over-clustering scenarios. In this paper, we propose a novel evaluation metric...