GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing

• URL: http://arxiv.org/abs/2501.06828v1
• Date: Sun, 12 Jan 2025 14:45:27 GMT
• Title: GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing
• Authors: Ruizhe Ou, Yuan Hu, Fan Zhang, Jiaxin Chen, Yu Liu,
• Abstract summary: GeoPix is a RS MLLM that extends image understanding capabilities to the pixel level. To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor. To address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset.
• Score: 22.729750410621826
• License:
• Abstract: Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from the vision encoder into masks conditioned on the LLM's segmentation token embeddings. To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor to capture and store class-wise geo-context at the instance level across the entire dataset. In addition, to address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset, comprising 65,463 images and 140,412 instances, with each instance annotated with text descriptions, bounding boxes, and masks. Furthermore, we develop a two-stage training strategy to balance the distinct requirements of text generation and masks prediction in multi-modal multi-task optimization. Extensive experiments verify the effectiveness and superiority of GeoPix in pixel-level segmentation tasks, while also maintaining competitive performance in image- and region-level benchmarks.

Related papers

• CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models [2.331828779757202]
  We introduce the new task of part-focused semantic co-segmentation, which seeks to identify and segment common and unique objects and parts across images. We present CALICO, the first LVLM that can segment and reason over multiple masks across images, enabling object comparison based on their constituent parts.
  arXiv  Detail & Related papers  (2024-12-26T18:59:37Z)
• RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts [17.76606110070648]
  We propose RSUniVLM, a unified, end-to-end RS VLM for comprehensive vision understanding across multiple granularity. RSUniVLM performs effectively in multi-image analysis, with instances of change detection and change captioning. We also construct a large-scale RS instruction-following dataset based on a variety of existing datasets in both RS and general domain.
  arXiv  Detail & Related papers  (2024-12-07T15:11:21Z)
• GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding [31.01378033872341]
  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.
  arXiv  Detail & Related papers  (2024-11-16T05:12:11Z)
• MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs [61.56904387052982]
  This paper proposes a new visual grounding task called multi-context visual grounding. It aims to localize instances of interest across multiple images based on open-ended text prompts. We benchmark over 20 state-of-the-art MLLMs and foundation models with potential multi-context visual grounding capabilities.
  arXiv  Detail & Related papers  (2024-10-16T07:52:57Z)
• AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding [96.01726275876548]
  We present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. Our model is capable of processing images with resolutions up to $1008times 1008$.
  arXiv  Detail & Related papers  (2024-08-30T03:16:49Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want [58.091825321168514]
  We introduce the Draw-and-Understand project: a new model, a multi-domain dataset, and a challenging benchmark for visual prompting. Specifically, we propose a new end-to-end trained Multimodal Large Language Model (MLLM) that connects a vision encoder, a visual prompt encoder and an LLM. To advance visual prompting research for MLLMs, we introduce MDVP-Data and MDVP-Bench.
  arXiv  Detail & Related papers  (2024-03-29T16:26:20Z)
• PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model [49.80313655590392]
  PSALM is a powerful extension of the Large Multi-modal Model (LMM) to address the segmentation task challenges. It incorporates a mask decoder and a well-designed input schema to handle a variety of segmentation tasks. The flexible design of PSALM supports joint training across multiple datasets and tasks, leading to improved performance and task generalization.
  arXiv  Detail & Related papers  (2024-03-21T17:50:47Z)
• Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
  We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references. Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
  arXiv  Detail & Related papers  (2024-03-05T13:45:46Z)
• Osprey: Pixel Understanding with Visual Instruction Tuning [15.094943732551018]
  Osprey is a mask-text instruction tuning approach to extend MLLMs by incorporating fine-grained mask regions into language instruction. To achieve this goal, we first curate a mask-based region-text dataset with 724K samples, and then design a vision-language model by injecting pixel-level representation into LLM. Specifically, Osprey adopts a convolutional CLIP backbone as the vision encoder and employs a mask-aware visual extractor to extract precise visual mask features from high resolution input.
  arXiv  Detail & Related papers  (2023-12-15T18:58:11Z)
• 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)

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.