Domain-Specific Self-Supervised Pre-training for Agricultural Disease Classification: A Hierarchical Vision Transformer Study

• URL: http://arxiv.org/abs/2601.11612v1
• Date: Fri, 09 Jan 2026 12:35:52 GMT
• Title: Domain-Specific Self-Supervised Pre-training for Agricultural Disease Classification: A Hierarchical Vision Transformer Study
• Abstract summary: We investigate the impact of domain-specific self-supervised pre-training on agricultural disease classification using hierarchical vision transformers.<n>Key finding is that SimCLR pre-training on just 3,000 unlabeled agricultural images provides a +4.57% accuracy improvement.<n>We show this SSL benefit is architecture-agnostic: applying the same pre-training to Swin-Base yields +4.08%, to ViT-Base +4.20%.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate the impact of domain-specific self-supervised pre-training on agricultural disease classification using hierarchical vision transformers. Our key finding is that SimCLR pre-training on just 3,000 unlabeled agricultural images provides a +4.57% accuracy improvement--exceeding the +3.70% gain from hierarchical architecture design. Critically, we show this SSL benefit is architecture-agnostic: applying the same pre-training to Swin-Base yields +4.08%, to ViT-Base +4.20%, confirming practitioners should prioritize domain data collection over architectural choices. Using HierarchicalViT (HVT), a Swin-style hierarchical transformer, we evaluate on three datasets: Cotton Leaf Disease (7 classes, 90.24%), PlantVillage (38 classes, 96.3%), and PlantDoc (27 classes, 87.1%). At matched parameter counts, HVT-Base (78M) achieves 88.91% vs. Swin-Base (88M) at 87.23%, a +1.68% improvement. For deployment reliability, we report calibration analysis showing HVT achieves 3.56% ECE (1.52% after temperature scaling). Code: https://github.com/w2sg-arnav/HierarchicalViT

Related papers

• Lightweight Vision Transformer Compression for On-Device Plant Disease Detection in Resource-Constrained Agricultural Field Conditions [1.5530227558314913]
  Vision Transformers (ViTs) have achieved high classification accuracy, but their large computational footprint makes deployment on resource constrained devices challenging.<n>We propose a unified Vision Transformer compression framework that combines H-BAC, guided by second-order sensitivity estimation, with quantization and attention-based knowledge distillation.
  arXiv  Detail & Related papers  (2026-09-04T16:40:06Z)
• PlantC2USeg: Cross-Scale Consistent Pre-Training for Few-Shot Unified Plant Point Cloud Segmentation [6.959027496658641]
  We propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning to align features across spatial scales.<n>The framework achieves the highest semantic IoU and instance mWCov among compared methods, at 91.91% and 94.62%.<n>Results demonstrate that PlantC2USeg reduces overall adaptation effort under distribution shifts, enabling scalable plant phenotyping and transferable 3D representation learning beyond agriculture.
  arXiv  Detail & Related papers  (2026-09-02T17:43:56Z)
• Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis [48.83701310501069]
  We introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for neural architecture search (NAS)<n>We evaluate the framework on OlympicCoder-7B within the LEMUR benchmark on CIFAR-10 image classification.<n>We report a cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum yields 27% peak SR at substantially lower accuracy (60.5%) than the CIFAR-10 equivalent.
  arXiv  Detail & Related papers  (2026-07-13T14:14:30Z)
• Enhancing Precision Agriculture with a Hybrid Deep Learning Framework for Multi-Class Plant Disease Classification and Interpretability [0.0]
  This study proposes an overall deep learning architecture for multi-class classification of plant diseases from high-resolution leaf imagery.<n>A specially gathered image database with 15,200 training images and 3,800 validation images spanned 38 classes across multiple crops, including tomato, apple, grape etc.<n>For every one of the considered architectures, ResNet-50 led to the highest accuracy of 98.74%, whereas the hybrid ResNet + ViT model achieved a competitive accuracy of 98.58%.
  arXiv  Detail & Related papers  (2026-06-13T12:41:31Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification [45.52399819498234]
  This work presents a systematic empirical comparison of three model paradigms for fine-grained crop disease classification.<n>We introduce AgriPath-LF16, a benchmark containing 111k images spanning 16 crops and 41 diseases.<n>CNNs achieve the highest accuracy on lab imagery but degrade under domain shift.<n> Contrastive VLMs provide a robust and parameter-efficient alternative with competitive cross-domain performance.
  arXiv  Detail & Related papers  (2026-03-08T17:28:01Z)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)
• Uncertainty-Aware Domain Adaptation for Vitiligo Segmentation in Clinical Photographs [4.19421520851419]
  Accurately quantifying vitiligo extent in routine clinical photographs is crucial for longitudinal monitoring of treatment response.<n>We propose a data-efficient training strategy combining domain-adaptive pre-training on the ISIC 2019 dataset with an ROI-based dual-task loss to suppress background noise.<n>Our framework demonstrates high reliability with zero catastrophic failures and provides interpretable entropy maps to identify ambiguous regions for clinician review.
  arXiv  Detail & Related papers  (2025-12-12T18:56:21Z)
• A Neural Affinity Framework for Abstract Reasoning: Diagnosing the Compositional Gap in Transformer Architectures via Procedural Task Taxonomy [0.0]
  We present the first 9-category taxonomy of all tasks, validated at 97.5% accuracy via rule-based code analysis.<n>We prove the taxonomy's visual coherence by training a CNN on raw grid pixels (95.24% accuracy on S3, 36.25% overall, 3.3x chance)<n>Our curriculum analysis reveals 35.3% of tasks exhibit low neural affinity for Transformers--a distributional bias mirroring ARC-AGI-2.
  arXiv  Detail & Related papers  (2025-12-08T02:46:00Z)
• When Do Domain-Specific Foundation Models Justify Their Cost? A Systematic Evaluation Across Retinal Imaging Tasks [0.0]
  We demonstrate that pretraining provides universal benefits (5.18-18.41% improvement), scaling with task difficulty.<n> compact general-purpose models deliver near-optimal performance for most retinal classification tasks.
  arXiv  Detail & Related papers  (2025-11-27T00:59:21Z)
• Validating Vision Transformers for Otoscopy: Performance and Data-Leakage Effects [42.465094107111646]
  This study evaluates the efficacy of vision transformer models, specifically Swin transformers, in enhancing the diagnostic accuracy of ear diseases.<n>The research utilised a real-world dataset from the Department of Otolaryngology at the Clinical Hospital of the Universidad de Chile.
  arXiv  Detail & Related papers  (2025-11-06T23:20:37Z)
• Mobile-Friendly Deep Learning for Plant Disease Detection: A Lightweight CNN Benchmark Across 101 Classes of 33 Crops [39.58317527488534]
  Plant diseases are a major threat to food security globally.<n>We have developed a mobile-friendly solution which can accurately classify 101 plant diseases across 33 crops.
  arXiv  Detail & Related papers  (2025-08-14T16:43:27Z)
• Enhancing Food-Domain Question Answering with a Multimodal Knowledge Graph: Hybrid QA Generation and Diversity Analysis [41.09752906121257]
  We propose a unified food-domain QA framework that combines a large-scale multimodal knowledge graph (MMKG) with generative AI.<n>Our MMKG links 13,000 recipes, 3,000 ingredients, 140,000 relations, and 14,000 images. We generate 40,000 QA pairs using 40 templates and LLaVA/DeepSeek augmentation.
  arXiv  Detail & Related papers  (2025-07-09T05:59:06Z)
• DExNet: Combining Observations of Domain Adapted Critics for Leaf Disease Classification with Limited Data [3.156688657641748]
  This work proposes a few-shot learning framework, Domain-adapted Expert Network (DExNet), for plant disease classification.<n>It starts with extracting the feature embeddings as 'observations' from nine 'critics' that are state-of-the-art pre-trained CNN-based architectures.<n>The proposed pipeline is evaluated on the 10 classes of tomato leaf images from the PlantVillage dataset.
  arXiv  Detail & Related papers  (2025-06-22T21:15:54Z)
• Hybrid Knowledge Transfer through Attention and Logit Distillation for On-Device Vision Systems in Agricultural IoT [0.0]
  This work advances real-time, energy-efficient crop monitoring in precision agriculture.<n>It demonstrates how we can attain ViT-level diagnostic precision on edge devices.
  arXiv  Detail & Related papers  (2025-04-21T06:56:41Z)
• Global Context Vision Transformers [78.5346173956383]
  We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. We address the lack of the inductive bias in ViTs, and propose to leverage a modified fused inverted residual blocks in our architecture. Our proposed GC ViT achieves state-of-the-art results across image classification, object detection and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2022-06-20T18:42:44Z)
• ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention [48.697458429460184]
  Two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer. This paper proposes a well-designed model named ERNIE-Sparse. It consists of two distinctive parts: (i) Hierarchical Sparse Transformer (HST) to sequentially unify local and global information, and (ii) Self-Attention Regularization (SAR) to minimize the distance for transformers with different attention topologies.
  arXiv  Detail & Related papers  (2022-03-23T08:47:01Z)
• Vision Transformers for femur fracture classification [59.99241204074268]
  The Vision Transformer (ViT) was able to correctly predict 83% of the test images. Good results were obtained in sub-fractures with the largest and richest dataset ever.
  arXiv  Detail & Related papers  (2021-08-07T10:12:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.