RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models

Key points

• Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis.1
• However, visual classifiers rely on predefined label spaces, CLIP-based methods perform recognition through static image-text alignment, and multimodal large language models (MLLMs) introduce unnecessary token-level generation for classification tasks with explicit candidate categories.1
• Specifically, we introduce a OnePass Decider that extracts multimodal decision states and directly estimates category probabilities within the candidate category space, eliminating autoregressive decoding while preserving vision-language interactions.1
• Extensive experiments on three widely used remote sensing scene classification benchmarks, including UC Merced, AID, and NWPU-RESISC45, demonstrate that RSJEV achieves superior classification performance compared with representative CNN-, Transformer-, Mamba-, CLIP-, and MLLM-based methods.1

Sources (1)

• [1]RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 03:28 PM

  To address these limitations, we propose RSJEV, a one-pass multimodal decision framework for remote sensing scene classification.

  Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis.

Extractive summary: sentences quoted from the sources.