paper-with-me

홈 › Papers

Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model

2025-02-13 · Shiryu Ueno, Yoshikazu Hayashi, Shunsuke Nakatsuka, Yusei Yamada, Hiroaki Aizawa, Kunihito Kato

We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high performance across various tasks, they are not trained on specific tasks such as visual inspection. Thus, we construct a dataset consisting of diverse images of non-defective and defective products collected from the web, along with unified formatted output text, and fine-tune VLM. For new products, our method employs In-Context Learning, which allows the model to perform inspections with an example of non-defective or defective image and the corresponding explanatory texts with visual prompts. This approach eliminates the need to collect a large number of training samples and re-train the model for each product. The experimental results show that our method achieves high performance, with MCC of 0.804 and F1-score of 0.950 on MVTec AD in a one-shot manner. Our code is available at~https://github.com/ia-gu/Vision-Language-In-Context-Learning-Driven-Few-Shot-Visual-Inspection-Model.

📄 PDF Abstract BibTeX arXiv:2502.09057

Code (1)

ia-gu/vision-language-in-context-learning-driven-few-shot-visual-inspection-model 공식 구현 pytorch

Tasks

In-Context LearningLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Good Questions Help Zero-Shot Image Reasoning

2023-12-04 · Kaiwen Yang, Tao Shen, Xinmei Tian, Xiubo Geng 외

Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained…

Fine-Grained Image ClassificationQuestion AnsweringVisual EntailmentVisual Question Answering

Teaching VLMs to Localize Specific Objects from In-context Examples

2024-11-20 · Sivan Doveh, Nimrod Shabtay, Wei Lin, Eli Schwartz 외

Vision-Language Models (VLMs) have shown remarkable capabilities across diverse visual tasks, including image recognition, video understanding, and Visual Question Answering (VQA) when explicitly trained for these tasks.…

ObjectObject TrackingQuestion AnsweringVideo Object Tracking+3

Generate, Transduct, Adapt: Iterative Transduction with VLMs

2025-01-10 · Oindrila Saha, Logan Lawrence, Grant van Horn, Subhransu Maji

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work…

AttributeTransductive LearningZero-Shot Learning

CoMa: Contextual Massing Generation with Vision-Language Models

2026-01-13 · Evgenii Maslov, Valentin Khrulkov, Anastasia Volkova, Anton Gusarov 외 arxiv

The conceptual design phase in architecture and urban planning, particularly building massing, is complex and heavily reliant on designer intuition and manual effort. To address this, we propose an automated framework fo…

Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation

2024-03-13 · ZiCheng Zhang, Tong Zhang, Yi Zhu, Jianzhuang Liu 외

The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its…

DecoderLanguage ModelingLanguage ModellingSemantic Segmentation+1