A Tiny CNN Architecture for Medical Face Mask Detection for Resource-Constrained Endpoints

基于单点监督的小目标检测

Tiny Object Detection with Single Point Supervision

针对小目标点标注噪声多、检测难的问题，提出采用两阶段去噪师生架构的Point Teacher方法，仅用点监督即可达到与框监督相当的小目标检测性能。

点到掩码：从任意点标注到掩码级红外小目标检测

Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection

本文提出Point-to-Mask框架，通过物理驱动的自适应掩码生成模块和轻量级半径感知点回归网络，将红外小目标检测转化为目标中心定位和有效半径回归，实现低成本点监督与掩码级检测的结合。

低分辨率监控图像上的戴口罩人脸分类基准

A Masked Face Classification Benchmark on Low-Resolution Surveillance Images

本文提出低分辨率戴口罩微小人脸分类数据集 SF-MASK，通过引入合成图像解决姿态多样性缺口，并支持多类分类，实验证明其能显著提升多种分类器的性能。

Effectiveness of Detection-based and Regression-based Approaches for Estimating Mask-Wearing Ratio

Estimating the mask-wearing ratio in public places is important as it enables health authorities to promptly analyze and implement policies. Methods for estimating the mask-wearing ratio on the basis of image analysis have been reported. However, there is still a lack of comprehensive research on both methodologies and datasets. Most recent reports straightforwardly propose estimating the ratio by applying conventional object detection and classification methods. It is feasible to use regression-based approaches to estimate the number of people wearing masks, especially for congested scenes wi…

CoSWA-YOLOv12：疟原虫的尺度不变微小目标检测与分割

CoSWA-YOLOv12: Scale-Invariant Tiny Object Detection and Segmentation of Malaria Parasites

CoSWA-YOLOv12通过尺度自适应Wasserstein分配、小波细节残差和M2-NWD损失，在保持预训练权重可迁移的同时，显著提升疟原虫微小目标检测与分割的召回率和定位精度。

Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images

Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform. This paper investigates optimizing the detection head based on the sparse convolution, which proves effective in balancing the accuracy and efficiency. Nevertheless, it suffers from inadequate integration of contextual information of tiny objects as well as clumsy control of the mask ratio in the presence of foreground with varying scales. To address the issues above, we propose a novel global context-enhanced adaptive sparse convolutional n…

S2HPruner：从软到硬的蒸馏弥合剪枝中的离散化鸿沟

S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning

针对可微掩码剪枝中软网络离散化为硬网络时存在的离散化鸿沟问题，提出S2HPruner框架，通过解耦双向知识蒸馏以单阶段弥合该鸿沟，在多基准和架构上无需微调即取得更优剪枝性能。

DualDiT：用于联合生成OCT图像与分割掩码的条件双输出扩散Transformer

DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation

该研究提出DualDiT模型，联合生成小鼠OCT图像与分割掩码，在生成质量、下游分割性能上优于DDPM、LDM，可用于医学图像数据增强

用于医学图像分割任务的潜在空间扩散模型

Diffusion Model in Latent Space for Medical Image Segmentation Task

MedSegLatDiff结合VAE和潜在扩散模型，通过加权交叉熵损失提升医学图像分割的精度与可靠性，适用于临床部署。

通过在最少标注 X 光片上进行鲁棒斑块提取实现脊柱骨赘检测

Spinal Osteophyte Detection via Robust Patch Extraction on minimally annotated X-rays

针对脊柱 X 光片中微小骨赘检测难题，本文提出结合深度学习椎骨分割与掩膜轮廓扩大的 SegPatch 自动斑块提取方法，在少量标注下显著优于基线。