计算机科学
人工智能
分割
模式识别(心理学)
注释
基本事实
集合(抽象数据类型)
语义学(计算机科学)
约束(计算机辅助设计)
交叉熵
一致性(知识库)
试验装置
熵(时间箭头)
图像分割
编码(内存)
计算机视觉
边界(拓扑)
一般化
图像(数学)
GSM演进的增强数据速率
感知
语义鸿沟
语义相似性
噪音(视频)
灵活性(工程)
接头(建筑物)
机器学习
特征(语言学)
代表(政治)
自然语言处理
神经编码
图像自动标注
作者
Yong Yang,Menglu Zhang,Tianci Wan
标识
DOI:10.1142/s0218001426550025
摘要
Weakly Supervised Semantic Segmentation(WSSS) reduces annotation costs but often suffers from incomplete target activation. To address this, we propose CAME(Cross-Attentive Multimodal Enhancement for Weakly-Supervised Referring Image Semantic Segmentation). CAME introduces CrossModalityAttnFusion(CMAF) to guide language features using visual cues, thereby improving semantic alignment. A Positional Encoding 2D(PED) module enhances structural perception through coordinate encoding. Structure-Aware Consistency Loss(SACL) enforces boundary alignment via edge constraints. Additionally, Entropy Constraint Loss and Focal Loss V2 suppress low-confidence noise and emphasize difficult regions. This joint optimization improves pseudo mask quality, resulting in sharper boundaries and enhanced regional consistency. Experiments show that CAME achieves mIoU scores of 54.96%, 57.08%, and 53.01% on the validation and test sets of RefCOCO, 48.25%, 46.37%, and 45.09% on RefCOCO+, and 54.89% on the validation set of RefCOCOg, significantly outperforming existing weakly supervised methods. These results confirm the effectiveness and strong generalization ability of the proposed approach.
科研通智能强力驱动
Strongly Powered by AbleSci AI