Adaptive Select Loss Strategy for Semantic Segmentation of Agricultural Crop Images

🧑 Corneliu Florea, Laura Florea, Mihai Ivanovici
📅 July 2025

We address the problem of agricultural image segmentation by introducing a novel loss formulation called Adaptive Select Loss (ASL), inspired by the Top-k loss strategy. While Top-k loss was originally designed for classification tasks, ASL is specifically tailored for semantic segmentation. It exploits the hierarchical structure of loss computation specific in semantic segmentation – aggregated first at the pixel level, then at the image level – while accounting for the imbalance between precise but scarce image-level annotations and noisy yet abundant pixel-level labels. ASL selectively aggregates loss from a “Few” (Top-k) of the most informative image-level instances and from “Almost all” (remove few) pixel-level data, thereby balancing robustness and sensitivity to noise. To ensure stability during training, we introduce a derivative smoothing mechanism that addresses the convergence issues introduced by the hard selection threshold, particularly when training with small number of images for loss aggregation. Empirically, the proposed approach improves boundary localization and segmentation quality in the presence of annotation noise. We evaluate ASL on three challenging semantic segmentation tasks—two agricultural and one mixed—using a visual transformer backbone, including hyperspectral data. ASL achieves consistent performance improvements, with gains of approximately 2.5% on hyperspectral and satellite imagery, and up to 6% on RGB-D data plant segmentation problem.

https://doi.org/10.1109/JSTARS.2025.3589635

NDVI and Beyond: Vegetation Indices as Features for Crop Recognition and Segmentation in Hyperspectral Data

🧑 Andreea Nițu, Corneliu Florea, Mihai Ivanovici, Andrei Racoviteanu
📅 June 2025

Vegetation indices have long been central to vegetation monitoring through remote sensing. The most popular one is the Normalized Difference Vegetation Index (NDVI), yet many vegetation indices (VIs) exist. In this paper, we investigate their distinctiveness and discriminative power in the context of applications for agriculture based on hyperspectral data. More precisely, this paper merges two complementary perspectives: an unsupervised analysis with PRISMA satellite imagery to explore whether these indices are truly distinct in practice and a supervised classification over UAV hyperspectral data. We assess their discriminative power, statistical correlations, and perceptual similarities. Our findings suggest that while many VIs have a certain correlation with the NDVI, meaningful differences emerge depending on landscape and application context, thus supporting their effectiveness as discriminative features usable in remote crop segmentation and recognition applications.

https://doi.org/10.3390/s25123817

Comparing Blind Image Quality Metrics for Reliable Image Assessment

🧑 Cristian George Fieraru, Maria Biserică, Ioana Cristina Plajer, Mihai Ivanovici
📅 June 2025

Reliable image quality assessment is essential not only in digital photography but also as a key metric for evaluating the performance of algorithms and models designed for image quality enhancement or generation. In recent years, a wide range of image quality assessment metrics, both traditional and learning-based, have been proposed, making it a challenge to select the appropriate method for a given task. This study presents a comparative analysis between five widely used traditional no-reference image quality assessment techniques and five machine learning-based approaches, evaluating their effectiveness in computing image quality scores. The evaluation is carried out comprehensively using a set of standard and advanced performance metrics. Furthermore, we analyze how characteristics of the training datasets, such as score distribution, influence model performance. The machine learning models considered vary significantly in architectural complexity, in terms of both the number of layers and parameters, and we investigate whether this variability has a considerable impact on prediction accuracy. The analysis also extends to non-photographic imagery, with a comparative evaluation of the methods on hyperspectral satellite image visualizations. For full transparency and reproducibility of the current study, all training parameters and hardware specifications are reported.

https://doi.org/10.1109/ACCESS.2025.3583029

Enhancing Domain-Specific Named Entity Recognition via Segmentation and Pseudo-Labeled Annotation (accepted at ICTAI 2025)

🧑 Pape Ibrahima Thiam, Yohann Chasseray, Josiane Mothe, Mathieu Roche, and Maguelonne Teisseire
📅 November 2025

Accepted as full paper in the Proceedings of the 37th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2025). 

This year ICTAI received a record 633 submissions in total. Of these,  only 133 were accepted as full papers (21.0% acceptance rate)

Territorial food systems, captured here through French-language documents, demand robust Named Entity Recognition (NER) despite scarce annotations and long, heterogeneous texts. In this work, we tackle two challenges: (1) segmenting long documents and (2) adapting open-schema NER to a specialized, low-resource domain. First, we compare four segmentation strategies in zero-shot settings to quantify precision–recall trade-offs. Then, we propose a semi-supervised pipeline that fine-tunes GLiNER and NuNER using a small manually annotated seed set followed by a large pseudo-labeled corpus built via cross-model agreement. Evaluations on a test set and the full annotated corpus show that pseudo-label fine-tuning consistently outperforms training on human-labeled data alone. The study also exposes strategy-specific strengths and weaknesses, underscoring that optimizing segmentation materially affects NER in domain-specific, low-resource scenarios. Our results provide practical guidance for deploying NER in territorial food systems and comparable specialized domains.

Code: https://github.com/ibzodiaz/segmentation-strategies