.png){kind=icon}
返回
Refactored Maskformer: Refactor localization and classification for improved universal image segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.displa.2025.102981.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The introduction of DEtection TRansformers (DETR) has marked a new era for universal image segmentation in computer vision. However, methods that use shared queries and attention layers for simultaneous localization and classification often encounter inter-task optimization conflicts. In this paper, we propose a novel architecture called Refactored Maskformer, which builds upon the Mask2Former through two key modifications: Decoupler and Reconciler. The Decoupler separates decoding pathways for localization and classification, enabling task-specific query and attention layer learning. Additionally, it employs a unified masked attention to confine the regions of interest for both tasks within the same object, along with a query Interactive-Attention layer to enhance task interaction. In the Reconciler module, we mitigate the optimization conflict issue by introducing localization supervised matching cost and task alignment learning loss functions. These functions aim to encourage high localization accuracy samples, while reducing the impact of high classification confidence samples with low localization accuracy on network optimization. Extensive experimental results demonstrate that our Refactored Maskformer achieves performance comparable to existing state-of-the-art models across all unified tasks, surpassing our baseline network, Mask2former, with 1.2% PQ on COCO, 6.8% AP on ADE20k, and 1.1% mIoU on Cityscapes. The code is available at https://github.com/leonzx7/Refactored-Maskformer.
Keyword:
Universal image segmentation
Inter-task optimization conflict
Task decoupling
Alignment learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.4
论文数:
2.3K
被引数:
3.2K
机构
引用论文
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
PREAI
分享收藏UniG-Encoder: A universal feature encoder for graph and hypergraph node classification.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcareNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容