Saved in:
Bibliographic Details
Main Authors: Hu, Suhang, Hu, Wei, Su, Yuhang, Zhang, Fan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.13229
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914037663531008
author Hu, Suhang
Hu, Wei
Su, Yuhang
Zhang, Fan
author_facet Hu, Suhang
Hu, Wei
Su, Yuhang
Zhang, Fan
contents Vision-Language Models (VLMs) struggle with complex image annotation tasks, such as emotion classification and context-driven object detection, which demand sophisticated reasoning. Standard Supervised Fine-Tuning (SFT) focuses solely on annotation outcomes, ignoring underlying rationales, while Visual Reinforcement Fine-Tuning (Visual-RFT) produces inconsistent Chains of Thought (CoTs) due to the absence of high-quality, verified CoTs during pre-training. We introduce RISE (Reason-Inspire-Strengthen-Expertise), a two-stage framework to overcome these limitations. In the Reason stage (RISE-CoT), a reinforcement learning-driven "annotation-reasoning-annotation" closed-loop generates visually grounded, logically consistent CoTs by verifying their ability to reconstruct original annotations without direct leakage. The Inspire and Strengthen stage (RISE-R1) leverages a high-quality CoT subset, filtered by RISE-CoT rewards, for supervised fine-tuning, followed by reinforcement fine-tuning to produce interpretable reasoning and accurate annotations, achieving Expertise in complex visual tasks. Evaluated on complex and simple image annotation tasks, RISE-trained Qwen2-VL-2B outperforms SFT and Visual-RFT, achieving robust performance and enhanced explainability. RISE offers a self-supervised solution for advancing VLM reasoning without requiring manually annotated CoTs.Code and resources are available at: https://github.com/HSH55/RISE.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13229
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning
Hu, Suhang
Hu, Wei
Su, Yuhang
Zhang, Fan
Machine Learning
Computer Vision and Pattern Recognition
Vision-Language Models (VLMs) struggle with complex image annotation tasks, such as emotion classification and context-driven object detection, which demand sophisticated reasoning. Standard Supervised Fine-Tuning (SFT) focuses solely on annotation outcomes, ignoring underlying rationales, while Visual Reinforcement Fine-Tuning (Visual-RFT) produces inconsistent Chains of Thought (CoTs) due to the absence of high-quality, verified CoTs during pre-training. We introduce RISE (Reason-Inspire-Strengthen-Expertise), a two-stage framework to overcome these limitations. In the Reason stage (RISE-CoT), a reinforcement learning-driven "annotation-reasoning-annotation" closed-loop generates visually grounded, logically consistent CoTs by verifying their ability to reconstruct original annotations without direct leakage. The Inspire and Strengthen stage (RISE-R1) leverages a high-quality CoT subset, filtered by RISE-CoT rewards, for supervised fine-tuning, followed by reinforcement fine-tuning to produce interpretable reasoning and accurate annotations, achieving Expertise in complex visual tasks. Evaluated on complex and simple image annotation tasks, RISE-trained Qwen2-VL-2B outperforms SFT and Visual-RFT, achieving robust performance and enhanced explainability. RISE offers a self-supervised solution for advancing VLM reasoning without requiring manually annotated CoTs.Code and resources are available at: https://github.com/HSH55/RISE.
title RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.13229