arXiv:2506.03213v2 Announce Type: replace 
Abstract: Plant Disease Detection (PDD) is a key aspect of precision agriculture. However, existing deep learning methods often rely on extensively annotated datasets, which are time-consuming and costly to generate. Self-supervised Learning (SSL) offers a promising alternative by exploiting the abundance of unlabeled data. However, most existing SSL approaches suffer from high computational costs due to convolutional neural networks or transformer-based architectures. Additionally, they struggle to capture long-range dependencies in visual representation and rely on static loss functions that fail to align local and global features effectively. To address these challenges, we propose ConMamba, a novel SSL framework specially designed for PDD. ConMamba integrates the Vision Mamba Encoder (VME), which employs a bidirectional State Space Model (SSM) to capture long-range dependencies efficiently. Furthermore, we introduce a dual-level contrastive loss with dynamic weight adjustment to optimize local-global feature alignment. Experimental results on three benchmark datasets demonstrate that ConMamba significantly outperforms state-of-the-art methods across multiple evaluation metrics. This provides an efficient and robust solution for PDD.

تم اقتراح إطار جديد للتعلم الذاتي المراقب يسمى ConMamba للكشف عن أمراض النباتات، حيث يعالج القيود المفروضة على طرق التعلم العميق الحالية التي تتطلب مجموعات بيانات موسعة تم التعليق عليها. يستخدم ConMamba مشفر Vision Mamba، الذي يدمج نموذج حالة ثنائي الاتجاه لالتقاط الاعتماديات بعيدة المدى بكفاءة في البيانات المرئية.

Se ha propuesto un nuevo marco de aprendizaje auto-supervisado llamado ConMamba para la detección de enfermedades en plantas, abordando las limitaciones de los métodos de aprendizaje profundo existentes que requieren conjuntos de datos anotados extensos. ConMamba utiliza el Codificador Vision Mamba, que incorpora un Modelo de Espacio de Estados bidireccional para capturar de manera eficiente las dependencias a largo plazo en los datos visuales.

Un nouveau cadre d'apprentissage auto-supervisé nommé ConMamba a été proposé pour la détection des maladies des plantes, répondant aux limites des méthodes d'apprentissage profond existantes qui nécessitent des ensembles de données annotées étendus. ConMamba utilise l'encodeur Vision Mamba, qui intègre un modèle d'état bidirectionnel pour capturer efficacement les dépendances à long terme dans les données visuelles.

A novel self-supervised learning framework named ConMamba has been proposed for plant disease detection, addressing the limitations of existing deep learning methods that require extensive annotated datasets. ConMamba utilizes the Vision Mamba Encoder, which incorporates a bidirectional State Space Model to efficiently capture long-range dependencies in visual data.

ConMamba: Contrastive Vision Mamba for Plant Disease Detection

arXiv:2511.18312v1 Announce Type: new 
Abstract: Time series data plays a pivotal role in a wide variety of fields but faces challenges related to privacy concerns. Recently, synthesizing data via diffusion models is viewed as a promising solution. However, existing methods still struggle to capture long-range temporal dependencies and complex channel interrelations. In this research, we aim to utilize the sequence modeling capability of a State Space Model called Mamba to extend its applicability to time series data generation. We firstly analyze the core limitations in State Space Model, namely the lack of consideration for correlated temporal lag and channel permutation. Building upon the insight, we propose Lag Fusion Mamba and Permutation Scanning Mamba, which enhance the model's ability to discern significant patterns during the denoising process. Theoretical analysis reveals that both variants exhibit a unified matrix multiplication framework with the original Mamba, offering a deeper understanding of our method. Finally, we integrate two variants and introduce Diffusion Mamba for Time Series (DiM-TS), a high-quality time series generation model that better preserves the temporal periodicity and inter-channel correlations. Comprehensive experiments on public datasets demonstrate the superiority of DiM-TS in generating realistic time series while preserving diverse properties of data.

تقدم دراسة جديدة نموذج DiM-TS، الذي يربط بين نماذج الفضاء الحالة الانتقائية وبيانات السلاسل الزمنية من أجل النمذجة التوليدية، حيث يتناول التحديات الكبيرة في توليد بيانات السلاسل الزمنية مع مراعاة مخاوف الخصوصية. تسلط الدراسة الضوء على القيود الموجودة في النماذج الحالية، لا سيما في التقاط الاعتماد الزمني على المدى الطويل والعلاقات المعقدة بين القنوات.

Un nuevo estudio presenta DiM-TS, un modelo que conecta los Modelos de Espacio de Estado Selectivos y los datos de series temporales para la modelización generativa, abordando desafíos significativos en la síntesis de datos de series temporales mientras se consideran las preocupaciones de privacidad. La investigación destaca las limitaciones de los modelos existentes, especialmente en la captura de dependencias temporales a largo plazo y relaciones complejas entre canales.

Une nouvelle étude présente DiM-TS, un modèle qui relie les modèles d'espace d'état sélectifs et les données de séries temporelles pour la modélisation générative, abordant des défis significatifs dans la synthèse des données de séries temporelles tout en tenant compte des préoccupations en matière de confidentialité. La recherche met en évidence les limitations des modèles existants, en particulier dans la capture des dépendances temporelles à long terme et des interrelations complexes entre les canaux.

A new study introduces DiM-TS, a model that bridges selective State Space Models and time series data for generative modeling, addressing significant challenges in synthesizing time series data while considering privacy concerns. The research highlights limitations in existing models, particularly in capturing long-range temporal dependencies and complex channel interrelations.

ConMamba: Contrastive Vision Mamba for Plant Disease Detection

Was this article worth reading? Share it

Attentive AI

Micro-Farms

Supametas.AI