Embeddings based Anomaly Detection for Cleaning Global Crop Type Reference Datasets

• URL: http://arxiv.org/abs/2607.23908v1
• Date: Mon, 27 Jul 2026 00:52:52 GMT
• Title: Embeddings based Anomaly Detection for Cleaning Global Crop Type Reference Datasets
• Abstract summary: We propose a practical, locality-aware, embedding-based anomaly (EBA) framework that operates on the embeddings of a pretrained Earth-observation encoder.<n>We score each labelled sample against other samples of the same crop in the same area using a pretrained embedding, flag the ones that stand out, and test whether removing or down-weighting them before training yields a better model.
• Score: 0.15404975601060747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High quality reference data remain a critical bottleneck for crop-type mapping at any spatial and temporal scale. Operational systems such as WorldCereal aggregate labels from heterogeneous sources such as parcel registers, national databases, field surveys, and map-derived products, each with their own biases, coverage gaps and unknown label noise. Simple global rules are inadequate, since crop phenology and observation conditions vary strongly across regions and seasons. In this study, we focus on a single, operationally relevant question: whether embeddings produced through geospatial foundation models are a viable basis for cleaning the reference data. We propose a practical, locality-aware, embedding-based anomaly (EBA) detection framework that operates on the embeddings of a pretrained Earth-observation encoder. We score each labelled sample against other samples of the same crop in the same area using a pretrained embedding, flag the ones that stand out, and test whether removing or down-weighting them before training yields a better model. We establish that the flagged points are genuinely mislabelled or misplaced in two independent ways: against synthetic ground truth, the detector concentrates injected label errors 2.5-5x above chance in its flagged set (detection AUROC up to 0.84); and on real data, a model-independent test shows that removing or confidence-weighting the flagged held-out points raises measured accuracy in trained models, for both crop type and land cover. Acting on the flags then improves the WorldCereal crop-type model across five macro-regions, evaluated on a fixed held-out split under three views. We find conservative cleaning helps while over-cleaning hurts. The EBA detector approach is designed to be reproducible and extensible, and can serve as a template for cleaning large, noisy Earth observation reference datasets beyond crop mapping.

Related papers

• On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift [13.021915223605681]
  We characterize where cross-dataset weed-localization performance degrades and which modeling choices recover it.<n>We evaluate the performance of several strategies for transferring a detector trained on one crop to another.
  arXiv  Detail & Related papers  (2026-08-21T16:06:09Z)
• Combating Noisy Labels through Fostering Self- and Neighbor-Consistency [120.4394402099635]
  Label noise is pervasive in various real-world scenarios, posing challenges in supervised deep learning.<n>We propose a noise-robust method named Jo-SNC (textbfJoint sample selection and model regularization based on textbfSelf- and textbfNeighbor-textbfConsistency)<n>We design a self-adaptive, data-driven thresholding scheme to adjust per-class selection thresholds.
  arXiv  Detail & Related papers  (2026-01-19T07:55:29Z)
• Coarse-to-Fine Hierarchical Alignment for UAV-based Human Detection using Diffusion Models [14.696438400081114]
  We introduce a three-stage diffusion-based framework designed to transform synthetic data for UAV-based human detection.<n>Cwd explicitly decouples global style and local content domain discrepancies and bridges those gaps using three modules.<n>Our method achieves up to $+14.1$ improvement of mAP50 on Semantic-Drone benchmark.
  arXiv  Detail & Related papers  (2025-12-15T19:57:36Z)
• Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data [0.0]
  This study explores unsupervised learning methods for automated anomaly detection in shearographic images.<n>Three architectures are evaluated: a fully connected autoencoder, a convolutional autoencoder, and a student-teacher model.<n>Results show that the student-teacher approach achieves superior classification and enables precise localization.
  arXiv  Detail & Related papers  (2025-11-04T12:48:02Z)
• Weed Detection in Challenging Field Conditions: A Semi-Supervised Framework for Overcoming Shadow Bias and Data Scarcity [7.019137213828947]
  This study tackles both issues through a diagnostic-driven, semi-supervised framework.<n>We use a unique dataset of approximately 975 labeled and 10,000 unlabeled images of Guinea Grass in sugarcane.<n>Our work provides a clear and field-tested framework for developing, diagnosing, and improving robust computer vision systems.
  arXiv  Detail & Related papers  (2025-08-27T01:55:47Z)
• Exploiting the Potential Supervision Information of Clean Samples in Partial Label Learning [8.969478423832188]
  We show that clean samples can be collected to offer guidance and enhance the confidence of the most possible candidates.<n>We attribute the most reliable candidates with higher significance under the assumption that for each clean sample, if its label is one of the candidates of its nearest neighbor in the representation space, it is more likely to be the ground truth of its neighbor.
  arXiv  Detail & Related papers  (2025-05-14T13:04:55Z)
• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection [50.343419243749054]
  Anomaly detection is critical in fields such as medical diagnostics and industrial defect detection.<n> CLIP's coarse-grained image-text alignment limits localization and detection performance for fine-grained anomalies.<n>Crane improves the state-of-the-art ZSAD from 2% to 28%, at both image and pixel levels, while remaining competitive in inference speed.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking [85.68235482145091]
  Large-scale speech datasets have become valuable intellectual property.<n>We propose a novel dataset ownership verification method.<n>Our approach introduces a clustering-based backdoor watermark (CBW)<n>We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-02T02:02:57Z)
• SAModified: A Foundation Model-Based Zero-Shot Approach for Refining Noisy Land-Use Land-Cover Maps [2.374912052693646]
  Land-use and land cover (LULC) analysis is critical in remote sensing.<n> automating LULC map generation using machine learning is rendered challenging due to noisy labels.<n>We propose a zero-shot approach using the foundation model, Segment Anything Model (SAM)<n>We achieve a significant reduction in label noise and an improvement in the performance of the downstream segmentation model by $approx 5%$ when trained with denoised labels.
  arXiv  Detail & Related papers  (2024-12-17T05:23:00Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Neighborhood Collective Estimation for Noisy Label Identification and Correction [92.20697827784426]
  Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. We propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors.
  arXiv  Detail & Related papers  (2022-08-05T14:47:22Z)
• SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining [76.95808270536318]
  We propose an end-to-end system that learns to separate proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions. We conduct exhaustive experiments on five splits on the PASCAL-VOC and COCO datasets achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-01-12T18:57:04Z)

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.