M$^3$HL：用于半监督医学图像分割的高低层特征一致性的互掩码混合

RISAM：基于互感知注意力特征的指代图像分割

RISAM: Referring Image Segmentation via Mutual-Aware Attention Features

针对现有指代图像分割方法易受视觉上下文主导、分割错误的问题，提出结合SAM与互感知注意力机制的MARIS方法，通过双向跨模态融合和多模态查询令牌提升分割准确性，在三个基准上超越现有最优水平。

用于内窥镜图像分割的扩散引导掩码一致配对混合

Diffusion-Guided Mask-Consistent Paired Mixing for Endoscopic Image Segmentation

针对内窥镜图像分割中的数据增强问题，提出扩散引导的配对混合方法MCPMix，结合保留标签的混合与扩散合成多样性，并采用RLA自适应调整混合强度与损失权重，在多个数据集上实现了最先进的分割性能与鲁棒泛化能力。

Co-Seg：用于组织和细胞核分割的相互提示引导协作学习

Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation

针对组织病理学中组织和细胞核分割任务被分离处理的问题，提出Co-Seg框架，通过区域感知提示编码器和相互提示掩码解码器实现两任务相互增强，在PUMA数据集上达到最先进性能。

多人体检测、姿态估计与分割：闭合良性循环

Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle

针对多人体近距离场景下姿态估计等任务性能不佳的问题，提出BBox-Mask-Pose闭环迭代方法，通过三个专用模型相互优化，在多数据集刷新三项任务SOTA，高重叠场景检测提升39%，是大型基础模型的高效替代。

Autoregressive Unsupervised Image Segmentation

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models that predict the current pixel from past pixels in a raster-scan ordering created with masked convolutions, we propose to use different orderings over the inputs using various forms of masked convolutions to construct different views of the data. For a given input, the model produces a pair of predictions with two valid orderings, and is then trained to maximize the mutual inf…

MixPro：面向视觉Transformer的MaskMix与渐进注意力标签数据增强

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

针对TransMix在图像裁剪和早期注意力图不可靠的问题，提出MaskMix与渐进注意力标签（PAL）相结合的数据增强方法MixPro，在ImageNet分类及多种下游任务上提升ViT模型的性能、迁移性和鲁棒性。

Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity

Object detection has achieved promising success, but requires large-scale fully-annotated data, which is time-consuming and labor-extensive. Therefore, we consider object detection with mixed supervision, which learns novel object categories using weak annotations with the help of full annotations of existing base object categories. Previous works using mixed supervision mainly learn the class-agnostic objectness from fully-annotated categories, which can be transferred to upgrade the weak annotations to pseudo full annotations for novel categories. In this paper, we further transfer mask prio…

Group-On：利用支持性查询增强单样本分割

Group-On: Boosting One-Shot Segmentation with Supportive Query

针对单样本语义分割中的类内变化问题，本文提出 Group-On，通过批量查询互为伪支持并结合 MoME 路由专家机制，显著提升性能。

MixReorg: 跨模态混合补丁重组是开放世界语义分割的良好掩码学习器

MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation

MixReorg通过跨图像混合补丁重组预训练，增强像素级语义对齐，使文本监督分割模型在开放世界零样本分割中显著超越GroupViT。

Boundary-preserving Mask R-CNN

Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object boundaries and shapes, leading coarse and indistinct mask prediction results and imprecise localization. To remedy these problems, we propose a conceptually simple yet effective Boundary-preserving Mask R-CNN (BMask R-CNN) to leverage object boundary information to improve mask localization accuracy. BMask R-CNN contains a boundary-preserving mask head in which objec…

Pseudo Mask Augmented Object Detection

In this work, we present a novel and effective framework to facilitate object detection with the instance-level segmentation information that is only supervised by bounding box annotation. Starting from the joint object detection and instance segmentation network, we propose to recursively estimate the pseudo ground-truth object masks from the instance-level object segmentation network training, and then enhance the detection network with top-down segmentation feedbacks. The pseudo ground truth mask and network parameters are optimized alternatively to mutually benefit each other. To obtain th…

A Fully Automated System for Sizing Nasal PAP Masks Using Facial Photographs

We present a fully automated system for sizing nasal Positive Airway Pressure (PAP) masks. The system is comprised of a mix of HOG object detectors as well as multiple convolutional neural network stages for facial landmark detection. The models were trained using samples from the publicly available PUT and MUCT datasets while transfer learning was also employed to improve the performance of the models on facial photographs of actual PAP mask users. The fully automated system demonstrated an overall accuracy of 64.71% in correctly selecting the appropriate mask size and 86.1% accuracy sizing w…

用于具有任意缺失模态的多模态脑肿瘤分割的语义引导掩码互学

Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities

针对多模态脑肿瘤分割中任意缺失模态导致性能下降的问题，提出语义引导掩码互学（SMML）方法，结合分层一致性约束双分支互学与SAM语义先验细化网络，有效提取鲁棒判别特征，在多个数据集上显著优于现有方法。