Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2402.17424

ViTaL: An Advanced Framework for Automated Plant Disease Identification in Leaf Images Using Vision Transformers and Linear Projection For Feature Reduction

Abhishek Sebastian·Annis Fathima A·Pragna R·Madhan Kumar S·Yaswanth Kannan G·Vinay Murali
View original source ↗Read source document ↗Export metadata ↓

Abstract

Our paper introduces a robust framework for the automated identification of diseases in plant leaf images. The framework incorporates several key stages to enhance disease recognition accuracy. In the pre-processing phase, a thumbnail resizing technique is employed to resize images, minimizing the loss of critical image details while ensuring computational efficiency. Normalization procedures are applied to standardize image data before feature extraction. Feature extraction is facilitated through a novel framework built upon Vision Transformers, a state-of-the-art approach in image analysis. Additionally, alternative versions of the framework with an added layer of linear projection and blockwise linear projections are explored. This comparative analysis allows for the evaluation of the impact of linear projection on feature extraction and overall model performance. To assess the effectiveness of the proposed framework, various Convolutional Neural Network (CNN) architectures are utilized, enabling a comprehensive evaluation of linear projection's influence on key evaluation metrics. The findings demonstrate the efficacy of the proposed framework, with the top-performing model achieving a Hamming loss of 0.054. Furthermore, we propose a novel hardware design specifically tailored for scanning diseased leaves in an omnidirectional fashion. The hardware implementation utilizes a Raspberry Pi Compute Module to address low-memory configurations, ensuring practicality and affordability. This innovative hardware solution enhances the overall feasibility and accessibility of the proposed automated disease identification system. This research contributes to the field of agriculture by offering valuable insights and tools for the early detection and management of plant diseases, potentially leading to improved crop yields and enhanced food security.

Explore related subjects

cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Abhishek Sebastian, Annis Fathima A, Pragna R, Madhan Kumar S, Yaswanth Kannan G, Vinay Murali. 2024-02-28. ViTaL: An Advanced Framework for Automated Plant Disease Identification in Leaf Images Using Vision Transformers and Linear Projection For Feature Reduction. https://doi.org/10.1007/978-981-97-6588-1_3

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

SSP-GNN: Learning to Track via Bilevel Optimization

We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identification features (attributes). Our method applies a successive shortest paths (SSP) algorithm to a tracking graph defined over a batch of frames. The edge costs in this tracking graph are computed via a message-passing network, a graph neural network (GNN) variant. The parameters of the GNN, and hence, the tracker, are learned end-to-end on a training set of example ground-truth tracks and detections. Specifically, learning takes the form of bilevel optimization guided by our novel loss function. We evaluate our algorithm on simulated scenarios to understand its sensitivity to scenario aspects and model hyperparameters. Across varied scenario complexities, our method compares favorably to a strong baseline.

cs.CV↗
arXiv2026

AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images

Cross-domain cell detection for microscopic images suffers from performance degradation due to distribution shifts across imaging domains. Unsupervised Domain Adaptation (UDA) strategies, attempt to overcome domain sift without requiring annotated data from target. However, requirement of availability of annotated data from the source domain and large-size data from target domain are both challenging limitations for realistic scenarios. This is especially true in medical imaging, where privacy requirements might prevent access to annotated source data, and costly data acquisition restricts extensive sampling of the target domain. To address these challenges, we propose AdaptiveCDM, a modular framework for Source-Free Few-Shot Domain Adaptive Object Detection (SF-FSDAOD) setting, that adapts a pretrained source model using only few labeled target images without accessing source data. AdaptiveCDM combines Resolution-Aware Augmentation (RAug) and Category-Aware Representation Learning (CARL). RAug alleviates the scarcity and class imbalance by augmenting instance balanced training examples, while preserving the scale fidelity and morphological properties of cellular structures. CARL enhances discriminative representation learning by encouraging class-consistent proposals, improving both localization and classification. We also introduce two competitive baselines for proposed setting: Faster-FreeShot and MT-FreeShot. Our approach achieves 40.4/43.4 mAP0.5 on M5 and 67.1/75.5 mAP0.5 on Raabin-WBC under 2-/5-shot adaptation. Despite using only a few labeled target images and no source data, AdaptiveCDM achieves competitive or superior performance compared with SOTA methods under their respective supervision settings. Ablations and qualitative analyses further substantiate the contribution of each component and the effectiveness of AdaptiveCDM in low-data regimes. Code/models will be available.

cs.CV↗
arXiv2026

Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection

Most existing video anomaly detectors rely on RGB frames alone, which limit their ability to capture abrupt or transient motion cues that are critical for identifying anomalous events. We propose Uncertainty Weighted Image Event Fusion (IEF-VAD), a framework that integrates complementary RGB and synthetic motion information through a principled weighting mechanism. The method models the high variance and heavy tailed characteristics of synthetic motion cues with a Student's t likelihood, computes value level inverse variance weights using a Laplace approximation to prevent the image modality from overshadowing motion information, and performs iterative refinement to suppress residual cross modal noise. This formulation provides a more balanced and reliable fusion process compared to cross attention or gating based approaches that often suffer from modality dominance. Without requiring an event camera or frame level annotations, IEF-VAD achieves new state of the art performance on multiple real world anomaly detection benchmarks and remains stable under degradation applied to individual modalities. The results indicate that extracting and integrating complementary motion cues is an effective direction for robust video understanding across diverse environments.

cs.CV↗