H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model

• URL: http://arxiv.org/abs/2403.20213v1
• Date: Fri, 29 Mar 2024 14:50:43 GMT
• Title: H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model
• Authors: Chao Pang, Jiang Wu, Jiayu Li, Yi Liu, Jiaxing Sun, Weijia Li, Xingxing Weng, Shuai Wang, Litong Feng, Gui-Song Xia, Conghui He,
• Abstract summary: Existing Remote Sensing specific Vision Language Models (RSVLMs) still have considerable potential for improvement. We constructed HqDC-1.4M, the large scale High quality and Detailed Captions for RS images, containing 1.4 million image-caption pairs. We developed RSSA, the first dataset aimed at enhancing the Self-Awareness capability of RSVLMs. Based on these datasets, we proposed the H2RSVLM, the Helpful and Honest Remote Sensing Vision Language Model.
• Score: 48.06425266787859
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The generic large Vision-Language Models (VLMs) is rapidly developing, but still perform poorly in Remote Sensing (RS) domain, which is due to the unique and specialized nature of RS imagery and the comparatively limited spatial perception of current VLMs. Existing Remote Sensing specific Vision Language Models (RSVLMs) still have considerable potential for improvement, primarily owing to the lack of large-scale, high-quality RS vision-language datasets. We constructed HqDC-1.4M, the large scale High quality and Detailed Captions for RS images, containing 1.4 million image-caption pairs, which not only enhance the RSVLM's understanding of RS images but also significantly improve the model's spatial perception abilities, such as localization and counting, thereby increasing the helpfulness of the RSVLM. Moreover, to address the inevitable "hallucination" problem in RSVLM, we developed RSSA, the first dataset aimed at enhancing the Self-Awareness capability of RSVLMs. By incorporating a variety of unanswerable questions into typical RS visual question-answering tasks, RSSA effectively improves the truthfulness and reduces the hallucinations of the model's outputs, thereby enhancing the honesty of the RSVLM. Based on these datasets, we proposed the H2RSVLM, the Helpful and Honest Remote Sensing Vision Language Model. H2RSVLM has achieved outstanding performance on multiple RS public datasets and is capable of recognizing and refusing to answer the unanswerable questions, effectively mitigating the incorrect generations. We will release the code, data and model weights at https://github.com/opendatalab/H2RSVLM .

Related papers

• Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method [10.748210940033484]
  Large language models (LLMs) and vision-language models (VLMs) have achieved significant success. Due to the substantial differences between remote sensing images and conventional optical images, these models face challenges in comprehension. This letter explores the application of VLMs for object detection in remote sensing images.
  arXiv  Detail & Related papers  (2025-03-11T08:02:54Z)
• Learning to Ground VLMs without Forgetting [54.033346088090674]
  We introduce LynX, a framework that equips pretrained Visual Language Models with visual grounding ability without forgetting their existing image and language understanding skills. To train the model effectively, we generate a high-quality synthetic dataset we call SCouT, which mimics human reasoning in visual grounding. We evaluate LynX on several object detection and visual grounding datasets, demonstrating strong performance in object detection, zero-shot localization and grounded reasoning.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding [41.74095171149082]
  We present a Versatile vision-language Benchmark for Remote Sensing image understanding, termed VRSBench. This benchmark comprises 29,614 images, with 29,614 human-verified detailed captions, 52,472 object references, and 123,221 question-answer pairs. We further evaluated state-of-the-art models on this benchmark for three vision-language tasks: image captioning, visual grounding, and visual question answering.
  arXiv  Detail & Related papers  (2024-06-18T08:15:21Z)
• SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing [14.79627534702196]
  We construct a vision-language dataset for remote sensing images, comprising 2.6 million image-text pairs covering 29K distinct semantic tags. With continual pre-training on this dataset, we obtain a VLM that surpasses baseline models with a 6.2% average accuracy gain in zero-shot scene classification. It also demonstrates the ability of zero-shot transfer for fine-grained object attribute classification and cross-modal retrieval.
  arXiv  Detail & Related papers  (2023-12-20T09:19:48Z)
• Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment [61.769441954135246]
  We introduce a method to train vision-language models for remote-sensing images without using any textual annotations. Our key insight is to use co-located internet imagery taken on the ground as an intermediary for connecting remote-sensing images and language.
  arXiv  Detail & Related papers  (2023-12-12T03:39:07Z)
• GeoChat: Grounded Large Vision-Language Model for Remote Sensing [65.78360056991247]
  We propose GeoChat - the first versatile remote sensing Large Vision-Language Models (VLMs) that offers multitask conversational capabilities with high-resolution RS images. Specifically, GeoChat can answer image-level queries but also accepts region inputs to hold region-specific dialogue. GeoChat demonstrates robust zero-shot performance on various RS tasks, e.g., image and region captioning, visual question answering, scene classification, visually grounded conversations and referring detection.
  arXiv  Detail & Related papers  (2023-11-24T18:59:10Z)
• CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding [38.53988682814626]
  We propose a context-enhanced masked image modeling method (CtxMIM) for remote sensing image understanding. CtxMIM formulates original image patches as a reconstructive template and employs a Siamese framework to operate on two sets of image patches. With the simple and elegant design, CtxMIM encourages the pre-training model to learn object-level or pixel-level features on a large-scale dataset.
  arXiv  Detail & Related papers  (2023-09-28T18:04:43Z)
• Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models [3.86170450233149]
  We show that large vision-and-language models (VLMs) trained to match images with text lack fine-grained understanding of spatial relations. We propose an alternative fine-grained, compositional approach for recognizing and ranking spatial clauses.
  arXiv  Detail & Related papers  (2023-08-18T18:58:54Z)
• Contextual Object Detection with Multimodal Large Language Models [66.15566719178327]
  We introduce a novel research problem of contextual object detection. Three representative scenarios are investigated, including the language cloze test, visual captioning, and question answering. We present ContextDET, a unified multimodal model that is capable of end-to-end differentiable modeling of visual-language contexts.
  arXiv  Detail & Related papers  (2023-05-29T17:50:33Z)
• Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense [98.70218717851665]
  It is unclear whether the models really understand the visual scene and underlying commonsense knowledge due to limited evaluation data resources. We present a Multimodal Evaluation (ME) pipeline to automatically generate question-answer pairs to test models' understanding of the visual scene, text, and related knowledge. We then take a step further to show that training with the ME data boosts the model's performance in standard VCR evaluation.
  arXiv  Detail & Related papers  (2022-11-10T21:44:33Z)
• RSVQA: Visual Question Answering for Remote Sensing Data [6.473307489370171]
  This paper introduces the task of visual question answering for remote sensing data (RSVQA) We use questions formulated in natural language and use them to interact with the images. The datasets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task.
  arXiv  Detail & Related papers  (2020-03-16T17:09:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.