mlsanityData to 14 Oct 2026

StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components

arXiv 2602.00703 ↗First posted 31 Jan 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Sorghum is a globally important cereal grown widely in water-limited and stress-prone regions. Its strong drought tolerance makes it a priority crop for climate-resilient agriculture. Improving water-use efficiency in sorghum requires precise characterisation of stomatal traits, as stomata control of gas exchange, transpiration and photosynthesis have a major influence on crop performance. Automated analysis of sorghum stomata is difficult because the stomata are small (often less than 40 μm in length in grasses such as sorghum) and vary in shape across genotypes and leaf surfaces. Automated segmentation contributes to high-throughput stomatal phenotyping, yet current methods still face challenges related to nested small structures and annotation bottlenecks. In this paper, we propose a semi-supervised instance segmentation framework tailored for analysis of sorghum stomatal components. We collect and annotate a sorghum leaf imagery dataset containing 11,060 human-annotated patches, covering the three stomatal components (pore, guard cell and complex area) across multiple genotypes and leaf surfaces. To improve the detection of tiny structures, we split high-resolution microscopy images into overlapping small patches. We then apply a pseudo-labelling strategy to unannotated images, producing an additional 56,428 pseudo-labelled patches. Benchmarking across semantic and instance segmentation models shows substantial performance gains: for semantic models the top mIoU increases from 65.93% to 70.35%, whereas for instance models the top AP rises from 28.30% to 46.10%. These results demonstrate that combining patch-based preprocessing with semi-supervised learning significantly improves the segmentation of fine stomatal structures. The proposed framework supports scalable extraction of stomatal traits and facilitates broader adoption of AI-driven phenotyping in crop science.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 75 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

33 of 75 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2017Mask R-CNNcited by 7,277
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  9. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  10. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  11. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  12. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
21 more
  1. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  2. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  3. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  4. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  5. 2020Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patchescited by 27
  6. 2023Zero-Shot Learning by Harnessing Adversarial Samplescited by 24
  7. 2019CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Languagecited by 23
  8. 2024Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baselinecited by 19
  9. 2024PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentationcited by 14
  10. 2021Mitigating Generation Shifts for Generalized Zero-Shot Learningcited by 13
  11. 2022GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learningcited by 12
  12. 2023Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentationcited by 12
  13. 2024Snap and Diagnose: An Advanced Multimodal Retrieval System for Identifying Plant Diseases in the Wildcited by 12
  14. 2025Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routingcited by 12
  15. 2024VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blockscited by 11
  16. 2024FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuningcited by 10
  17. 2025Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptationcited by 7
  18. 2024CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstructioncited by 5
  19. 2024MatchSeg: Towards Better Segmentation via Reference Image Matchingcited by 4
  20. 2025Augment to Segment: Tackling Pixel-Level Imbalance in Wheat Disease and Pest Segmentationcited by 3
  21. 2025Distributed Zero-Shot Learning for Visual Recognitioncited by 3

Built on by

Not cited yet.