← Back to all news
arXiv Computer Vision By Md Nadim Mahamood, Md Arif Shahriar, Md Shafi Ud Doula, Kamrul Hasan

CoAtNet-DeepMoE: A Convolution-Attention Hybrid with DeepSeek Mixture-of-Experts for Parameter-Efficient Tomato Disease Classification

Read the original on arXiv Computer Vision →

CoAtNet-DeepMoE is a lightweight Convolution‑Attention hybrid architecture that incorporates a DeepSeek Mixture‑of‑Experts to reduce parameters while maintaining high accuracy for tomato disease classification. The model achieves state‑of‑the‑art performance on Kaggle and PlantVillage datasets, reporting 99.80% accuracy on Kaggle and 99.83% accuracy on PlantVillage, all with only 2.47 million parameters. The source code will be released on GitHub.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jun 2

Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift

arXiv:2606. 02045v1 Announce Type: cross Abstract: Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management.

By Adri\'an C\'anovas-Rodriguez, Miguel A. Gonz\'alez-Ill\'an, Maria Fernanda Garc\'ia-Cruz, Pedro Nortes Tortosa, Jos\'e Salvador Rubio-Asensio, Miguel A. Zamora Izquierdo, Juan Antonio Mart\'inez Navarro, Antonio F. Skarmeta
fine-tuningbenchmarks
More like this →
arXiv Computer Vision
Aug 24

A Dataset-Centric Benchmark of Deep Learning Methods for Grape Leaf Disease Classification and Detection

The paper introduces a dataset‑centric benchmark for deep learning approaches to grape leaf disease classification and detection. It evaluates publicly available datasets on disease categories, annotations, acquisition conditions, and class distributions, and tests representative models across image‑level classification, region‑level classification, and object detection. Results reveal high accuracy on controlled datasets but significant performance drops on heterogeneous, real‑world data, especially in cross‑dataset transfer and object detection tasks.

By Petar Canoski, Vlatko Spasev, Ivica Dimitrovski, Ivan Kitanovski, Petre Lameski
computer-visionbenchmarks
More like this →