paper-with-me

홈 › Papers

TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition

2024-09-23 · Guoyang Zhao, Fulong Ma, Weiqing Qi, Chenguang Zhang, Yuxuan Liu, Ming Liu, Jun Ma

Traffic sign is a critical map feature for navigation and traffic control. Nevertheless, current methods for traffic sign recognition rely on traditional deep learning models, which typically suffer from significant performance degradation considering the variations in data distribution across different regions. In this paper, we propose TSCLIP, a robust fine-tuning approach with the contrastive language-image pre-training (CLIP) model for worldwide cross-regional traffic sign recognition. We first curate a cross-regional traffic sign benchmark dataset by combining data from ten different sources. Then, we propose a prompt engineering scheme tailored to the characteristics of traffic signs, which involves specific scene descriptions and corresponding rules to generate targeted text descriptions for optimizing the model training process. During the TSCLIP fine-tuning process, we implement adaptive dynamic weight ensembling (ADWE) to seamlessly incorporate outcomes from each training iteration with the zero-shot CLIP model. This approach ensures that the model retains its ability to generalize while acquiring new knowledge about traffic signs. Our method surpasses conventional classification benchmark models in cross-regional traffic sign evaluations, and it achieves state-of-the-art performance compared to existing CLIP fine-tuning techniques. To the best knowledge of authors, TSCLIP is the first contrastive language-image model used for the worldwide cross-regional traffic sign recognition task. The project website is available at: https://github.com/guoyangzhao/TSCLIP.

📄 PDF Abstract BibTeX arXiv:2409.15077

Code (1)

guoyangzhao/tsclip 공식 구현

Tasks

Prompt EngineeringTraffic Sign Recognition

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

2025-01-01 · CVPR 2025 1 · Zelin Peng, Zhengqin Xu, Zhilin Zeng, Changsong Wen 외

CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing the text encoder preserves its powerful embeddings, recent studies show that fine-t…

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic Segmentation

Meta CLIP 2: A Worldwide Scaling Recipe

2025-07-29 · Yung-Sung Chuang, Yang Li, Dong Wang, Ching-Feng Yeh 외 arxiv

Contrastive Language-Image Pretraining (CLIP) is a popular foundation model, supporting from zero-shot classification, retrieval to encoders for multimodal large language models (MLLMs). Although CLIP is successfully tra…

Image-to-Text Retrieval

Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP

2026-01-14 · Anant Mehta, Xiyuan Wei, Xingyu Chen, Tianbao Yang arxiv

CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different que…

Representation Learning

CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

2022-12-12 · Xiaoyi Dong, Jianmin Bao, Ting Zhang, Dongdong Chen 외

Recent studies have shown that CLIP has achieved remarkable success in performing zero-shot inference while its fine-tuning performance is not satisfactory. In this paper, we identify that fine-tuning performance is sign…

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

2024-05-29 · CVPR 2025 1 · Zelin Peng, Zhengqin Xu, Zhilin Zeng, Yaoming Wang 외

Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. Vision-language foundation models, especially CLIP, have recently emerged as powerful tools for acquiring open…

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic Segmentationparameter-efficient fine-tuningSemantic Segmentation