Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909714815647744 |
|---|---|
| author | Chung, Sangyun Yu, Youngjoon Kim, Se Yeon Chee, Youngchae Ro, Yong Man |
| author_facet | Chung, Sangyun Yu, Youngjoon Kim, Se Yeon Chee, Youngchae Ro, Yong Man |
| contents | Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In this paper, we revisit and analyze these limitations and introduce a novel, cost-efficient paradigm that significantly advances sensor image understanding-without requiring extensive training data or any modifications to the existing VLM architectures. Specifically, we propose Sensor-Aware Attributes Fine-Tuning (SAFT) with the Diverse Negative Attributes (DNA) optimization, which leverages minimal sensor-specific data to enable robust learning of non-RGB characteristics and overcome RGB-centric biases inherent in current VLMs. In addition, we present VS-TDX-the first comprehensive, public benchmark designed to rigorously evaluate VLMs' sensor-specific understanding across diverse and realistic scenarios. Through extensive experiments on VLMs and various sensor modalities, we validate that our method consistently delivers superior performance and generalization under resource-constrained and architecture-invariant settings. Our approach provides a practical advance towards scalable deployment of VLMs in increasingly sensor-diverse real-world environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20750 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking Chung, Sangyun Yu, Youngjoon Kim, Se Yeon Chee, Youngchae Ro, Yong Man Computer Vision and Pattern Recognition Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In this paper, we revisit and analyze these limitations and introduce a novel, cost-efficient paradigm that significantly advances sensor image understanding-without requiring extensive training data or any modifications to the existing VLM architectures. Specifically, we propose Sensor-Aware Attributes Fine-Tuning (SAFT) with the Diverse Negative Attributes (DNA) optimization, which leverages minimal sensor-specific data to enable robust learning of non-RGB characteristics and overcome RGB-centric biases inherent in current VLMs. In addition, we present VS-TDX-the first comprehensive, public benchmark designed to rigorously evaluate VLMs' sensor-specific understanding across diverse and realistic scenarios. Through extensive experiments on VLMs and various sensor modalities, we validate that our method consistently delivers superior performance and generalization under resource-constrained and architecture-invariant settings. Our approach provides a practical advance towards scalable deployment of VLMs in increasingly sensor-diverse real-world environments. |
| title | Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.20750 |