|国家预印本平台
首页|Stable Diffusion Models are Secretly Good at Visual In-Context Learning

Stable Diffusion Models are Secretly Good at Visual In-Context Learning

Stable Diffusion Models are Secretly Good at Visual In-Context Learning

来源:Arxiv_logoArxiv
英文摘要

Large language models (LLM) in natural language processing (NLP) have demonstrated great potential for in-context learning (ICL) -- the ability to leverage a few sets of example prompts to adapt to various tasks without having to explicitly update the model weights. ICL has recently been explored for computer vision tasks with promising early outcomes. These approaches involve specialized training and/or additional data that complicate the process and limit its generalizability. In this work, we show that off-the-shelf Stable Diffusion models can be repurposed for visual in-context learning (V-ICL). Specifically, we formulate an in-place attention re-computation within the self-attention layers of the Stable Diffusion architecture that explicitly incorporates context between the query and example prompts. Without any additional fine-tuning, we show that this repurposed Stable Diffusion model is able to adapt to six different tasks: foreground segmentation, single object detection, semantic segmentation, keypoint detection, edge detection, and colorization. For example, the proposed approach improves the mean intersection over union (mIoU) for the foreground segmentation task on Pascal-5i dataset by 8.9% and 3.2% over recent methods such as Visual Prompting and IMProv, respectively. Additionally, we show that the proposed method is able to effectively leverage multiple prompts through ensembling to infer the task better and further improve the performance.

Trevine Oorloff、Vishwanath Sindagi、Wele Gedara Chaminda Bandara、Ali Shafahi、Amin Ghiasi、Charan Prakash、Reza Ardekani

计算技术、计算机技术

Trevine Oorloff,Vishwanath Sindagi,Wele Gedara Chaminda Bandara,Ali Shafahi,Amin Ghiasi,Charan Prakash,Reza Ardekani.Stable Diffusion Models are Secretly Good at Visual In-Context Learning[EB/OL].(2025-08-13)[2025-08-24].https://arxiv.org/abs/2508.09949.点此复制

评论