A simple image segmentation framework via in-context examples

[Free GPT-4]
[PDF] arxiv.org

Unleashing the potential of the diffusion model in few-shot semantic segmentation

M Zhu, Y Liu, Z Luo, C **g, H Chen, G Xu… - arxiv preprint arxiv …, 2024 - arxiv.org
The Diffusion Model has not only garnered noteworthy achievements in the realm of image
generation but has also demonstrated its potential as an effective pretraining method …
保存 引用 被引用次数：2 相关文章 所有 3 个版本 HTML 版
[Free GPT-4]
[PDF] arxiv.org

There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks

M Espinosa, C Yang, L Ericsson, S McDonagh… - arxiv preprint arxiv …, 2024 - arxiv.org
The Segment Anything Model (SAM) was originally designed for label-agnostic mask
generation. Does this model also possess inherent semantic understanding, of value to …
保存 引用 相关文章 HTML 版
[Free GPT-4]
[PDF] arxiv.org

Vision and Language Reference Prompt into SAM for Few-shot Segmentation

K Sakurai, R Shimizu, M Goto - arxiv preprint arxiv:2502.00719, 2025 - arxiv.org
Segment Anything Model (SAM) represents a large-scale segmentation model that enables
powerful zero-shot capabilities with flexible prompts. While SAM can segment any object in …
保存 引用 相关文章 HTML 版