TasselNetV4: A vision foundation model for cross-scene, cross-scale, and cross-species plant counting

• URL: http://arxiv.org/abs/2509.20857v1
• Date: Thu, 25 Sep 2025 07:48:29 GMT
• Title: TasselNetV4: A vision foundation model for cross-scene, cross-scale, and cross-species plant counting
• Abstract summary: We introduce TasselNetV4, shifting from species-specific counting to cross-species counting.<n>It builds upon a plain vision transformer and incorporates novel multi-branch box-aware local counters.<n>Our results indicate that TasselNetV4 emerges to be a vision foundation model for cross-scene, cross-scale, and cross-species plant counting.
• Score: 10.520978148046026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate plant counting provides valuable information for agriculture such as crop yield prediction, plant density assessment, and phenotype quantification. Vision-based approaches are currently the mainstream solution. Prior art typically uses a detection or a regression model to count a specific plant. However, plants have biodiversity, and new cultivars are increasingly bred each year. It is almost impossible to exhaust and build all species-dependent counting models. Inspired by class-agnostic counting (CAC) in computer vision, we argue that it is time to rethink the problem formulation of plant counting, from what plants to count to how to count plants. In contrast to most daily objects with spatial and temporal invariance, plants are dynamic, changing with time and space. Their non-rigid structure often leads to worse performance than counting rigid instances like heads and cars such that current CAC and open-world detection models are suboptimal to count plants. In this work, we inherit the vein of the TasselNet plant counting model and introduce a new extension, TasselNetV4, shifting from species-specific counting to cross-species counting. TasselNetV4 marries the local counting idea of TasselNet with the extract-and-match paradigm in CAC. It builds upon a plain vision transformer and incorporates novel multi-branch box-aware local counters used to enhance cross-scale robustness. Two challenging datasets, PAC-105 and PAC-Somalia, are harvested. Extensive experiments against state-of-the-art CAC models show that TasselNetV4 achieves not only superior counting performance but also high efficiency.Our results indicate that TasselNetV4 emerges to be a vision foundation model for cross-scene, cross-scale, and cross-species plant counting.

Related papers

• Count Anything [41.17667085289094]
  We study text-guided object counting across domains, where a model takes an image and a natural-language query as input and returns an instance-grounded set of target points.<n>Based on CLOC, we propose Count Anything, a generalist model for text-guided object counting.
  arXiv  Detail & Related papers  (2026-05-29T05:08:31Z)
• Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species [9.22893600241327]
  TPC-268 is the first plant counting benchmark incorporating plant taxonomy.<n>The dataset features 10,000 images with 678,050 point annotations.<n>It includes 268 countable plant categories over 242 plant species in Plantae and Fungi.
  arXiv  Detail & Related papers  (2026-03-22T13:37:00Z)
• CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping [43.24254323363639]
  We propose a level-aware vision language framework that jointly predicts plant age and leaf count using a single multi-task model built on CLIP embeddings.<n>Our method aggregates rotational views into angle-invariant representations and conditions visual features on lightweight text priors encoding viewpoint level for stable prediction under incomplete or unordered inputs.<n>On the GroMo25 benchmark, our approach reduces mean age MAE from 7.74 to 3.91 and mean leaf-count MAE from 5.52 to 3.08 compared to the GroMo baseline, corresponding to improvements of 49.5% and 44.2%, respectively.
  arXiv  Detail & Related papers  (2026-03-04T14:01:47Z)
• Object-Centric 3D Gaussian Splatting for Strawberry Plant Reconstruction and Phenotyping [21.752518657362888]
  Strawberries are among the most economically significant fruits in the United States, generating over $2 billion in annual farm-gate sales.<n>Traditional plant phenotyping methods are time-consuming, labor-intensive, and often destructive.<n>We propose a novel object-centric 3D reconstruction framework incorporating a preprocessing pipeline.
  arXiv  Detail & Related papers  (2025-11-04T02:55:46Z)
• TriggerNet: A Novel Explainable AI Framework for Red Palm Mite Detection and Multi-Model Comparison and Heuristic-Guided Annotation [0.0]
  The red palm mite infestation has become a serious concern, particularly in regions with extensive palm cultivation.<n>The current study focuses on evaluating and comparing the ML model for classifying the affected plants and detecting the infestation.<n> TriggerNet is a novel interpretable AI framework that integrates Grad-CAM, RISE, FullGrad, and TCAV.
  arXiv  Detail & Related papers  (2025-10-20T19:23:17Z)
• Unlocking Zero-Shot Plant Segmentation with Pl@ntNet Intelligence [3.7603674895765766]
  We present a zero-shot segmentation approach for agricultural imagery.<n>Our method exploits Plantnet's specialized plant representations to identify plant regions.<n>We show consistent performance gains when using Plantnet-fine-tuned DinoV2 over the base DinoV2 model.
  arXiv  Detail & Related papers  (2025-10-14T14:38:32Z)
• Multi-output Deep-Supervised Classifier Chains for Plant Pathology [12.004640584906666]
  We propose a new model named Multi-Supervised Chains (Mo-DsCC) which weaves the prediction of plant species and disease by chaining the output layers for the two labels.<n>To evaluate the advantages of our model, we perform intensive experiments on two benchmark datasets.
  arXiv  Detail & Related papers  (2025-07-27T04:23:17Z)
• CountMamba: Exploring Multi-directional Selective State-Space Models for Plant Counting [33.41299696340091]
  Plant counting is essential in every stage of agriculture, including seed breeding, germination, cultivation, fertilization, pollination yield estimation, and harvesting. Inspired by the fact that humans count objects in high-resolution images by sequential scanning, we explore the potential of handling plant counting tasks via state space models (SSMs) for generating counting results. We propose a new counting approach named CountMamba that constructs multiple counting experts to scan from various directions simultaneously.
  arXiv  Detail & Related papers  (2024-10-10T01:52:57Z)
• Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method [84.68818879525568]
  We present a Concept Drift and Long-Tailed Distribution dataset. The characteristics of instances tend to vary with time and exhibit a long-tailed distribution. We propose a feature recombination framework to address the learning challenges associated with CDLT.
  arXiv  Detail & Related papers  (2023-06-04T12:42:45Z)
• CounTR: Transformer-based Generalised Visual Counting [94.54725247039441]
  We develop a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars" We conduct thorough ablation studies on the large-scale counting benchmark, e.g. FSC-147, and demonstrate state-of-the-art performance on both zero and few-shot settings.
  arXiv  Detail & Related papers  (2022-08-29T17:02:45Z)
• Vision Transformers For Weeds and Crops Classification Of High Resolution UAV Images [3.1083892213758104]
  Vision Transformer (ViT) models can achieve competitive or better results without applying any convolution operations. Our experiments show that with small set of labelled training data, ViT models perform better compared to state-of-the-art CNN-based models.
  arXiv  Detail & Related papers  (2021-09-06T19:58:54Z)
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery [56.10033255997329]
  We propose a novel deep learning method based on a Convolutional Neural Network (CNN) It simultaneously detects and geolocates plantation-rows while counting its plants considering highly-dense plantation configurations. The proposed method achieved state-of-the-art performance for counting and geolocating plants and plant-rows in UAV images from different types of crops.
  arXiv  Detail & Related papers  (2020-12-31T18:51:17Z)
• One-Shot Learning with Triplet Loss for Vegetation Classification Tasks [45.82374977939355]
  Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification.
  arXiv  Detail & Related papers  (2020-12-14T10:44:22Z)
• Unsupervised Domain Adaptation For Plant Organ Counting [12.424350934766704]
  Counting plant organs for image-based plant phenotyping falls within this category. In this paper, we propose a domain-adrial learning approach for domain adaptation of density map estimation.
  arXiv  Detail & Related papers  (2020-09-02T13:57:09Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)

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.