CVMay 28, 2023

AIMS: All-Inclusive Multi-Level Segmentation

arXiv:2305.17768v16 citations
Originality Incremental advance
AI Analysis

This addresses the need for multi-level segmentation in image editing applications, though it appears incremental as it builds on existing segmentation work with a unified multi-task approach.

The paper tackles the problem of diverse region-of-interest selections in image editing by proposing a new task called All-Inclusive Multi-Level Segmentation (AIMS), which segments images into part, entity, and relation levels, and demonstrates its effectiveness through experiments showing generalization capacity compared to state-of-the-art methods.

Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved. In this paper, we propose a new task, All-Inclusive Multi-Level Segmentation (AIMS), which segments visual regions into three levels: part, entity, and relation (two entities with some semantic relationships). We also build a unified AIMS model through multi-dataset multi-task training to address the two major challenges of annotation inconsistency and task correlation. Specifically, we propose task complementarity, association, and prompt mask encoder for three-level predictions. Extensive experiments demonstrate the effectiveness and generalization capacity of our method compared to other state-of-the-art methods on a single dataset or the concurrent work on segmenting anything. We will make our code and training model publicly available.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes