Remote-Sensing Image Classification

Latest papers

• A PyTorch Library for Hyperspectral Image Models: Technical Report

  Tanishq Rachamalla, Aryan Das, Srishti Kaushik, Swalpa Kumar Roy · 5 October 2026

  Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and self supervised masked autoencoding. Yet progress remains hindered by fragmented repositories, incompa…

• Unsupervised Domain Adaptation for Enhanced Radiometer Image Precipitation Estimation using Conditional Flow Matching

  Victor Enescu, Assaad Zeghina, Matthieu Meignin, Nicolas Viltard, C\'ecile Mallet · 2 October 2026

  Deep generative networks have recently achieved unprecedented performance in precise image and video editing using sophisticated textual prompts. However, the effectiveness of such models heavily depends on access to very large supervised and annotated image datasets, which can be very difficult to …

• Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing

  Rishabh Mondal, Nipun Batra, Utkarsh Mall · 1 October 2026

  While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability and expert interaction, they are either too expensive to train for the remote sensing domain or perform poorly without annotation. We posit that in e…

• Band-Selection Stability and Semantic Segmentation Performance: A Study on Hyperspectral City

  Jiarong Li, Imad Ali Shah, Enda Ward, Martin Glavin, Edward Jones, Brian Deegan · 28 September 2026

  Resource constraints make high-dimensional hyperspectral imaging challenging in autonomous perception, motivating the use of band selection methods. However, the sensitivity of band-selection methods to sampled data and their relationship to semantic segmentation models (SSMs) remain underexplored. …

• Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification

  Yimin Zhu, Mahmood Elahi, Lincoln Linlin Xu · 25 September 2026

  Although hyperspectral images (HSIs) provide rich spectral-spatial information, accurate pixel-level classification remains challenging because of spectral-spatial heterogeneity and complex spatial structures. Existing vision state space models (Mamba) typically construct sequences according to pred…

• Semantic-Guided Fusion Network for Multi-Source Remote Sensing Image Classification

  Yuwei Zhao, Chuanzheng Gong, Baogui Huan, Feng Gao, Junyu Dong, Qian Du · 24 September 2026

  Multi-source remote sensing image classification has attracted increasing attention due to the complementary spectral, structural, and geometric information. However, existing methods still suffer from two limitations: insufficient semantic contextual modeling and unreliable feature fusion caused by…

• Benchmarking Hyperspectral Foundation Models for Hyperspectral Unmixing

  Edgard Dabier, Christophe Kervazo, Pietro Gori, Florence Tupin · 24 September 2026

  Several foundation models dedicated to hyperspectral images have recently been made available. These models are trained on large unlabeled datasets and exhibit strong performance on many hyperspectral imaging tasks, such as classification or denoising. Nonetheless, their performance for hyperspectra…

• From Change Captions to Change Detection: Semantic-Appearance Agreement Framework for Remote Sensing Change Detection

  Yuan Qian, Jie Ma · 24 September 2026

  Remote sensing change detection (RSCD) is essential for monitoring land-cover changes and urban development. However, most methods demand pixel-level change masks, which are costly and time-consuming to annotate. Weakly supervised methods reduce this cost by using image-level change labels. Yet thes…

• Temporally Ordered Region-Token Mamba with Logit-Space Diffusion for Remote Sensing Change Detection

  Anuvab Sen, Maneet Chatterjee, Aparup Ghosh, Udayon Sen, Arnav Aditya, Yixin Zhang · 24 September 2026

  Remote sensing change detection requires both global reasoning across bitemporal images and precise localization of changed regions. However, dense attention is computationally expensive for high-resolution imagery, while conventional feature fusion and coarse decoding may inadequately separate genu…

• MGRL-RSCC: Multi-Granularity Reward Reinforcement Learning for Fine-Grained Remote Sensing Change Captioning

  Futian Wang, Mengqi Wang, Xiao Wang, Wentao Wu, Haowen Wang, Zhicheng Zhao, Jin Tang · 23 September 2026

  Remote Sensing Change Captioning (RSCC), which aims to generate accurate and detailed linguistic descriptions of ground object variations from bi-temporal remote sensing images, is a critical and challenging task in intelligent remote sensing interpretation. The mainstream autoregressive training pa…

• RSPDBench: Benchmarking Vision Foundation Models on Earth Observation Tasks Under Physically Grounded Remote-Sensing Product Degradations

  Tanjim Bin Faruk, Khondaker Masfiq Reza, Shrideep Pallickara, Sangmi Lee Pallickara · 22 September 2026

  Vision foundation models targeting Earth observation (EO) tasks are commonly evaluated on clean downstream benchmarks, but operational EO products can already contain spatial, radiometric, alignment, noise, and harmonization defects before reaching the model. Existing robustness evaluations often us…

• SatOV: Restoring Spatial Priors for Training-Free Open-Vocabulary Segmentation in Remote Sensing Imagery

  Changhao Zhao, Linglin Zeng, Hai Liu · 22 September 2026

  Open-vocabulary semantic segmentation (OVS) of remote sensing imagery is a challenging pixel-level task requiring strong generalization and adaptation to the spatial characteristics of remote sensing data. Although existing vision-language foundation models perform well in general domains, their ima…

• From Pixels to Images: A Structural Survey of Deep Learning Paradigms in Remote Sensing Image Semantic Segmentation

  Quanwei Liu, Tao Huang, Jiaqi Yang, Wei Xiang · 16 September 2026

  Remote sensing images (RSIs) capture both natural and human-induced changes on the Earth's surface. Semantic segmentation (SS) of RSIs enables the fine-grained interpretation of surface features, making it a critical task in RS analysis. With the increasing diversity and volume of RSIs collected by …

• VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation

  Quanwei Liu, Tao Huang, Jiaqi Yang, Wei Xiang · 16 September 2026

  Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe performance degradation under a coupled dual-drift paradigm: visual domain drift from cross-spatial-reso…

• Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis

  Subash Khanal, Yangzhi Cui, Daniel Cher, Eric Xing, Brian Wei, Srikumar Sastry, Nathan Jacobs · 14 September 2026

  Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramids that nest fine detail within wide coverage. Current generative models of satellite imagery, however, operate along a single axis: they either zoom…

• Beyond Weak Labels: Prompt-Guided Local Refinement for Weakly Supervised Water Segmentation in High-Resolution Multispectral Imagery

  Muhammad Farhan Humayun, Mohammad Imangholiloo, Afifah Shah, Tomi Westerlund, Jukka Heikkonen · 10 September 2026

  High-resolution water mapping supports environmental monitoring and related applications, but accurate pixel-level labels are difficult and costly to produce. Official hydrographic vectors provide scalable weak supervision, but they contain artifacts like boundary noise, temporal mismatch, and omiss…

• Dimensionality Reduction for Hyperspectral Image Classification

  Mohamed Cherifi, Ammar Mesloub, Mohammed Nabil El Korso, Tayeb Touhami, Abdennour Hacine Gharbi · 10 September 2026

  This paper addresses the issue of supervised classification in the context of hyperspectral satellite images. It deals with two fundamental aspects: dimensionality reduction of data and the selection of appropriate supervised classification techniques. Firstly, we delve into dimensionality reducti…

• From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection

  Xiao An, Ruikang Zhang, Chen Zhong, Xuli Shen, Jiaxing Sun, Jiang Wu, Wei He · 10 September 2026

  Dense change detection in remote sensing requires vision-language models (VLMs) to compare bi-temporal images and generate accurate pixel-level masks. Existing VLMs are largely confined to change captioning outputs, and the few that produce pixel-level masks still rely on external decoders or flat t…

• Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery

  Wuzhou Li, Jiawei Zhou, Shenghang Wang, Xiang Li · 10 September 2026

  Open-world object detection (OWOD) extends closed-set detection by requiring models to identify unknown objects and incrementally learn them once annotations become available. In remote sensing imagery, object categories often exhibit latent hierarchical relationships that may be inadequately repres…

• AGSA-Net: Abundance-Guided Self-Attention Network for Spectral Unmixing-Aware Hyperspectral Remote Sensing Image Classification

  Nafisa Anjum, Satavisa Dey Borno, Ananna Saha, Mir Faiyaz Hossain, Sifat Momen, Nabeel Mohammed, Shafin Rahman · 9 September 2026

  Hyperspectral image (HSI) classification plays a vital role in remote sensing applications, including agriculture, environmental monitoring, and urban analysis. However, its performance remains challenged by high spectral redundancy, noise sensitivity, and the difficulty of jointly modeling local ma…

• MEOX: Compact Multimodal Mixture-of-Experts for Earth Observation

  Mohanad Albughdadi · 7 September 2026

  Recent advances in Earth Observation representation learning accommodate heterogeneous sensors and missing observations, often through larger architectures. We present MEOX (Multimodal Earth Observation with eXperts), a multimodal masked autoencoder with a 2.939 million-parameter encoder and 3.115 m…

• Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data

  Xiangyang Miao, Kelu Yao, Yekai Huang, Xiaogang Xu, Junxiao Xue, Minjun Shen, Chenghui Lv, Shanji Liu, Yaying Chen, Chao Li · 4 September 2026

  Contrastive language-image learning (CLIP) has become a key paradigm for remote sensing vision-language understanding. However, existing remote sensing contrastive learning methods are mostly built on RGB-oriented CLIP architectures, making it difficult to exploit heterogeneous sensors such as SAR, …

• Agentic Multimodal Models for Environmental Hyperspectral Unmixing

  Micha{\l} Cholewa, Luca Ciampi, Nicola Messina, Przemys{\l}aw G{\l}omb, Giuseppe Amato · 2 September 2026

  Hyperspectral unmixing is a key task in remote sensing that aims to decompose mixed pixels in hyperspectral images into their constituent material signatures, or endmembers, and their fractional abundances. Conventional modular approaches estimate the scene composition through successive model-order…

• RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing

  Kaiyue Kang, Qixuan He, Peijin Wang, Yingchao Feng, Chao Ren, Kangxin Wang, Wenhui Diao, Yixiao Wang, Liangjin Zhao, Kaiwen Wei, Nayu Liu, Xian Sun · 2 September 2026

  Remote sensing visual models have continuously advanced various interpretation tasks. However, the research process behind model improvement still heavily relies on manual expertise, requiring extensive trial-and-error iterations in model design, data processing, and performance diagnosis. Existing …

• Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing

  Keyan Hu, Mingtao Wang, Ziyu Zhou, Tiandong Shi, Haifeng Li, Ji Qi, Chao Tao · 31 August 2026

  Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods jointly learn the target prior and cross-modal dependence from scarce paired data, overlooking a key asymmetry: only the latter intrinsically requires…