摘要
The recent advancements in large-scale pre-training techniques have significantly enhanced the capabilities of vision foundation models, notably the Segment Anything Model (SAM), which can generate precise masks based on point and box prompts. Recent studies extend SAM to Few-shot Semantic Segmentation (FSS), focusing on prompt generation for SAM-based automatic semantic segmentation. However, these methods struggle with selecting suitable prompts, require specific hyperparameter settings for different scenarios, and experience prolonged one-shot inference time due to the overuse of SAM, resulting in low efficiency and limited automation ability. To address these issues, we propose a simple yet effective approach based on graph analysis. In particular, a Positive-Negative Alignment module dynamically selects the point prompts for generating masks, especially uncovering the potential of the background context as the negative reference. Another subsequent Point-Mask Clustering module aligns the granularity of masks and selected points as a directed graph, based on mask coverage over points. These points are then aggregated by decomposing the weakly connected components of the directed graph in an efficient manner, constructing distinct natural clusters. Finally, the positive and overshooting gating, benefiting from graph-based granularity alignment, aggregate high-confident masks and filter out the false-positive masks for final prediction, without relying on additional hyperparameters and redundant mask generation. Extensive experimental analysis across tasks including the standard FSS, One-shot Part Segmentation, and Cross Domain FSS validate the effectiveness and efficiency of the proposed approach, surpassing state-of-the-art generalist models with a mIoU of 58.7% on COCO-20i and 35.2% on LVIS-92i. The project page of this work is: https://andyzaq.github.io/GF-SAM/.
| 源语言 | 英语 |
|---|---|
| 期刊 | Advances in Neural Information Processing Systems |
| 卷 | 37 |
| 出版状态 | 已出版 - 2024 |
| 已对外发布 | 是 |
| 活动 | 38th Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver, 加拿大 期限: 9 12月 2024 → 15 12月 2024 |
学术指纹
探究 'Bridge the Points: Graph-based Few-shot Segment Anything Semantically' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver