GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding

• URL: http://arxiv.org/abs/2411.11904v1
• Date: Sat, 16 Nov 2024 05:12:11 GMT
• Title: GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding
• Authors: Yue Zhou, Mengcheng Lan, Xiang Li, Yiping Ke, Xue Jiang, Litong Feng, Wayne Zhang,
• Abstract summary: GeoGround is a novel framework that unifies support for HBB, OBB, and mask RS visual grounding tasks. To support model training, we present refGeo, a large-scale RS visual instruction-following dataset containing 161k image-text pairs.
• Score: 31.01378033872341
• License:
• Abstract: Remote sensing (RS) visual grounding aims to use natural language expression to locate specific objects (in the form of the bounding box or segmentation mask) in RS images, enhancing human interaction with intelligent RS interpretation systems. Early research in this area was primarily based on horizontal bounding boxes (HBBs), but as more diverse RS datasets have become available, tasks involving oriented bounding boxes (OBBs) and segmentation masks have emerged. In practical applications, different targets require different grounding types: HBB can localize an object's position, OBB provides its orientation, and mask depicts its shape. However, existing specialized methods are typically tailored to a single type of RS visual grounding task and are hard to generalize across tasks. In contrast, large vision-language models (VLMs) exhibit powerful multi-task learning capabilities but struggle to handle dense prediction tasks like segmentation. This paper proposes GeoGround, a novel framework that unifies support for HBB, OBB, and mask RS visual grounding tasks, allowing flexible output selection. Rather than customizing the architecture of VLM, our work aims to elegantly support pixel-level visual grounding output through the Text-Mask technique. We define prompt-assisted and geometry-guided learning to enhance consistency across different signals. To support model training, we present refGeo, a large-scale RS visual instruction-following dataset containing 161k image-text pairs. Experimental results show that GeoGround demonstrates strong performance across four RS visual grounding tasks, matching or surpassing the performance of specialized methods on multiple benchmarks. Code available at https://github.com/zytx121/GeoGround

Related papers

• EarthMarker: Visual Prompt Learning for Region-level and Point-level Remote Sensing Imagery Comprehension [12.9701635989222]
  The first visual prompting model named EarthMarker is proposed, which excels in image-level, region-level, and point-level RS imagery interpretation. To endow the EarthMarker with versatile multi-granularity visual perception abilities, the cross-domain phased learning strategy is developed. To tackle the lack of RS visual prompting data, a dataset named RSVP featuring multi-modal fine-grained visual prompting instruction is constructed.
  arXiv  Detail & Related papers  (2024-07-18T15:35:00Z)
• ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization [0.0]
  We propose a two-stage training method to enhance visual performance and use contrastive learning to mine challenging samples. We validate the effectiveness of the proposed strategy on several large-scale visual geo-localization datasets.
  arXiv  Detail & Related papers  (2024-06-04T02:28:51Z)
• Evaluating Tool-Augmented Agents in Remote Sensing Platforms [1.8434042562191815]
  Existing benchmarks assume question-answering input templates over predefined image-text data pairs. We present GeoLLM-QA, a benchmark designed to capture long sequences of verbal, visual, and click-based actions on a real UI platform.
  arXiv  Detail & Related papers  (2024-04-23T20:37:24Z)
• Aligning and Prompting Everything All at Once for Universal Visual Perception [79.96124061108728]
  APE is a universal visual perception model for aligning and prompting everything all at once in an image to perform diverse tasks. APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection. Experiments on over 160 datasets demonstrate that APE outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-04T18:59:50Z)
• 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)
• GLaMM: Pixel Grounding Large Multimodal Model [57.91763410032292]
  We present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM is flexible enough to accept both textual and optional visual prompts (region of interest) as input. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale.
  arXiv  Detail & Related papers  (2023-11-06T18:59:57Z)
• RRSIS: Referring Remote Sensing Image Segmentation [25.538406069768662]
  Localizing desired objects from remote sensing images is of great use in practical applications. Referring image segmentation, which aims at segmenting out the objects to which a given expression refers, has been extensively studied in natural images. We introduce referring remote sensing image segmentation (RRSIS) to fill in this gap and make some insightful explorations.
  arXiv  Detail & Related papers  (2023-06-14T16:40:19Z)
• Vision Transformers: From Semantic Segmentation to Dense Prediction [139.15562023284187]
  We explore the global context learning potentials of vision transformers (ViTs) for dense visual prediction. Our motivation is that through learning global context at full receptive field layer by layer, ViTs may capture stronger long-range dependency information. We formulate a family of Hierarchical Local-Global (HLG) Transformers, characterized by local attention within windows and global-attention across windows in a pyramidal architecture.
  arXiv  Detail & Related papers  (2022-07-19T15:49:35Z)
• AF$_2$: Adaptive Focus Framework for Aerial Imagery Segmentation [86.44683367028914]
  Aerial imagery segmentation has some unique challenges, the most critical one among which lies in foreground-background imbalance. We propose Adaptive Focus Framework (AF$), which adopts a hierarchical segmentation procedure and focuses on adaptively utilizing multi-scale representations. AF$ has significantly improved the accuracy on three widely used aerial benchmarks, as fast as the mainstream method.
  arXiv  Detail & Related papers  (2022-02-18T10:14:45Z)
• Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning [126.57680291438128]
  We study whether scalability can be achieved via a disentangled representation. We evaluate semantic tracklets' on the visual multi-agent particle environment (VMPE) and on the challenging visual multi-agent GFootball environment. Notably, this method is the first to successfully learn a strategy for five players in the GFootball environment using only visual data.
  arXiv  Detail & Related papers  (2021-08-06T22:19:09Z)

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.