# Cross-domain Multi-step Thinking: Zero-shot Fine-grained Traffic Sign Recognition in the Wild

arXiv: https://arxiv.org/abs/2409.01534 · HTML: https://mlsanity.com/paper/2409.01534/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 75 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles](https://mlsanity.com/paper/2309.10228/) (2023)
- [LMEye: An Interactive Perception Network for Large Language Models](https://mlsanity.com/paper/2305.03701/) (2023)

## Abstract (arXiv)

In this study, we propose Cross-domain Multi-step Thinking (CdMT) to improve zero-shot fine-grained traffic sign recognition (TSR) performance in the wild. Zero-shot fine-grained TSR in the wild is challenging due to the cross-domain problem between clean template traffic signs and real-world counterparts, and existing approaches particularly struggle with cross-country TSR scenarios, where traffic signs typically differ between countries. The proposed CdMT framework tackles these challenges by leveraging the multi-step reasoning capabilities of large multimodal models (LMMs). We introduce context, characteristic, and differential descriptions to design multiple thinking processes for LMMs. Context descriptions, which are enhanced by center coordinate prompt optimization, enable the precise localization of target traffic signs in complex road images and filter irrelevant responses via novel prior traffic sign hypotheses. Characteristic descriptions, which are derived from in-context learning with template traffic signs, bridge cross-domain gaps and enhance fine-grained TSR. Differential descriptions refine the multimodal reasoning ability of LMMs by distinguishing subtle differences among similar signs. CdMT is independent of training data and requires only simple and uniform instructions, enabling it to achieve cross-country TSR. We conducted extensive experiments on three benchmark datasets and two real-world datasets from different countries. The proposed CdMT framework achieved superior performance compared with other state-of-the-art methods on all five datasets, with recognition accuracies of 0.93, 0.89, 0.97, 0.89, and 0.85 on the GTSRB, BTSD, TT-100K, Sapporo, and Yokohama datasets, respectively.