Augment to Segment: Tackling Pixel-Level Imbalance in Wheat Disease and Pest Segmentation
- URL: http://arxiv.org/abs/2509.09961v1
- Date: Fri, 12 Sep 2025 04:38:32 GMT
- Title: Augment to Segment: Tackling Pixel-Level Imbalance in Wheat Disease and Pest Segmentation
- Authors: Tianqi Wei, Xin Yu, Zhi Chen, Scott Chapman, Zi Huang,
- Abstract summary: Insect damage occupies only a tiny fraction of annotated pixels.<n>This extreme pixel-level imbalance poses a significant challenge to the segmentation performance.<n>We propose a Random Projected Copy-and-Paste (RPCP) augmentation technique to address the pixel imbalance problem.
- Score: 34.461133608619015
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Accurate segmentation of foliar diseases and insect damage in wheat is crucial for effective crop management and disease control. However, the insect damage typically occupies only a tiny fraction of annotated pixels. This extreme pixel-level imbalance poses a significant challenge to the segmentation performance, which can result in overfitting to common classes and insufficient learning of rare classes, thereby impairing overall performance. In this paper, we propose a Random Projected Copy-and-Paste (RPCP) augmentation technique to address the pixel imbalance problem. Specifically, we extract rare insect-damage patches from annotated training images and apply random geometric transformations to simulate variations. The transformed patches are then pasted in appropriate regions while avoiding overlaps with lesions or existing damaged regions. In addition, we apply a random projection filter to the pasted regions, refining local features and ensuring a natural blend with the new background. Experiments show that our method substantially improves segmentation performance on the insect damage class, while maintaining or even slightly enhancing accuracy on other categories. Our results highlight the effectiveness of targeted augmentation in mitigating extreme pixel imbalance, offering a straightforward yet effective solution for agricultural segmentation problems.
Related papers
- Mitigating Spurious Correlations in Patch-wise Tumor Classification on High-Resolution Multimodal Images [7.481035149436658]
We show that patch-wise binary classification can introduce spurious correlations between patch composition and labels.<n>We propose a debiasing strategy to mitigate this effect.<n>This enhancement boosts model performance on critical minority cases.
arXiv Detail & Related papers (2025-11-17T16:01:30Z) - Active Adversarial Noise Suppression for Image Forgery Localization [56.98050814363447]
We introduce an Adversarial Noise Suppression Module (ANSM) that generate a defensive perturbation to suppress the attack effect of adversarial noise.<n>To our best knowledge, this is the first report of adversarial defense in image forgery localization tasks.
arXiv Detail & Related papers (2025-06-15T14:53:27Z) - Efficient Classification of Histopathology Images [5.749787074942512]
We use images with annotated tumor regions to identify a set of tumor patches and a set of benign patches in a cancerous slide.
This creates an important problem during patch-level classification, where the majority of patches from an image labeled as 'cancerous' are actually tumor-free.
arXiv Detail & Related papers (2024-09-08T17:41:04Z) - Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training [61.61368146268329]
We propose Pixel-reweighted AdveRsarial Training (PART), a new framework that partially reduces $epsilon$ for less influential pixels.
Part achieves a notable improvement in accuracy without compromising robustness on CIFAR-10, SVHN and TinyImagenet-200.
arXiv Detail & Related papers (2024-06-02T09:43:34Z) - Classification of Breast Cancer Histopathology Images using a Modified Supervised Contrastive Learning Method [4.303291247305105]
We improve the supervised contrastive learning method by leveraging both image-level labels and domain-specific augmentations to enhance model robustness.
We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images.
This improvement corresponds to 93.63% absolute accuracy, highlighting the effectiveness of our approach in leveraging properties of data to learn more appropriate representation space.
arXiv Detail & Related papers (2024-05-06T17:06:11Z) - AMLP:Adaptive Masking Lesion Patches for Self-supervised Medical Image
Segmentation [67.97926983664676]
Self-supervised masked image modeling has shown promising results on natural images.
However, directly applying such methods to medical images remains challenging.
We propose a novel self-supervised medical image segmentation framework, Adaptive Masking Lesion Patches (AMLP)
arXiv Detail & Related papers (2023-09-08T13:18:10Z) - Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer
for Exposure Correction [65.5397271106534]
A single neural network is difficult to handle all exposure problems.
In particular, convolutions hinder the ability to restore faithful color or details on extremely over-/under- exposed regions.
We propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction.
arXiv Detail & Related papers (2023-09-02T09:07:36Z) - Cross-Site Severity Assessment of COVID-19 from CT Images via Domain
Adaptation [64.59521853145368]
Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event.
To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites.
This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features.
arXiv Detail & Related papers (2021-09-08T07:56:51Z) - Overcoming the limitations of patch-based learning to detect cancer in
whole slide images [0.15658704610960567]
Whole slide images (WSIs) pose unique challenges when training deep learning models.
We outline the differences between patch or slide-level classification versus methods that need to localize or segment cancer accurately across the whole slide.
We propose a negative data sampling strategy, which drastically reduces the false positive rate and improves each metric pertinent to our problem.
arXiv Detail & Related papers (2020-12-01T16:37:18Z) - Quantification of groundnut leaf defects using image processing
algorithms [0.0]
The present work attempts to estimate the percentage of affected groundnut leaves area across four regions of Andharapradesh using image processing techniques.
The image analysis results across these four regions reveal that around 14 - 28% of leaves area is affected across the groundnut field.
arXiv Detail & Related papers (2020-06-11T15:07:12Z)
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.