Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2503.23330 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915218755420160 |
|---|---|
| author | Jiang, Hongxiang Yin, Jihao Wang, Qixiong Feng, Jiaqi Chen, Guo |
| author_facet | Jiang, Hongxiang Yin, Jihao Wang, Qixiong Feng, Jiaqi Chen, Guo |
| contents | Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges to existing MLLMs, which struggle with object-centric tasks, particularly in precise localization and fine-grained attribute description for each object. These RS MLLMs have not yet surpassed classical visual perception models, as they only provide coarse image understanding, leading to limited gains in real-world scenarios. To address this gap, we establish EagleVision, an MLLM tailored for remote sensing that excels in object detection and attribute comprehension. Equipped with the Attribute Disentangle module, EagleVision learns disentanglement vision tokens to express distinct attributes. To support object-level visual-language alignment, we construct EVAttrs-95K, the first large-scale object attribute understanding dataset in RS for instruction tuning, along with a novel evaluation benchmark, EVBench. EagleVision achieves state-of-the-art performance on both fine-grained object detection and object attribute understanding tasks, highlighting the mutual promotion between detection and understanding capabilities in MLLMs. The code, model, data, and demo will be available at https://github.com/XiangTodayEatsWhat/EagleVision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing Jiang, Hongxiang Yin, Jihao Wang, Qixiong Feng, Jiaqi Chen, Guo Computer Vision and Pattern Recognition Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges to existing MLLMs, which struggle with object-centric tasks, particularly in precise localization and fine-grained attribute description for each object. These RS MLLMs have not yet surpassed classical visual perception models, as they only provide coarse image understanding, leading to limited gains in real-world scenarios. To address this gap, we establish EagleVision, an MLLM tailored for remote sensing that excels in object detection and attribute comprehension. Equipped with the Attribute Disentangle module, EagleVision learns disentanglement vision tokens to express distinct attributes. To support object-level visual-language alignment, we construct EVAttrs-95K, the first large-scale object attribute understanding dataset in RS for instruction tuning, along with a novel evaluation benchmark, EVBench. EagleVision achieves state-of-the-art performance on both fine-grained object detection and object attribute understanding tasks, highlighting the mutual promotion between detection and understanding capabilities in MLLMs. The code, model, data, and demo will be available at https://github.com/XiangTodayEatsWhat/EagleVision. |
| title | EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23330 |