Aug 2026· iScience· Vol 29, pp. 117234· 0 citations· 50 references
Medicine
TL;DR
DEPFIN is an annotation-free image analysis pipeline that combines foreground segmentation, frozen pretrained convolutional encoders, non-linear dimensionality reduction, and density-based clustering for extracting biological structure from the growing volumes of unlabeled fish imagery.
Abstract
Summary Automating fish image classification would relieve a growing annotation bottleneck in ecology, developmental biology, and fisheries science, where imagery accumulates far faster than experts can label it. We present DEEPFIN, an annotation-free image analysis pipeline that combines foreground segmentation, frozen pretrained convolutional encoders, non-linear dimensionality reduction, and density-based clustering. DEEPFIN recovers the seven canonical developmental stages of the clownfish Amphiprion ocellaris with 87% cluster-to-class accuracy and separates three congeneric anemonefish species from images alone. Independent validation across three public datasets spanning in situ underwater, multi-condition, and controlled ground-truth-masked imaging yields consistent pairwise species discrimination without labels, matching or approaching contemporary supervised methods on the same data. Beyond replicating expert categories, the pipeline surfaces intra-class variation that fixed-label classifiers cannot expose. DEEPFIN is a lightweight, generalizable framework for extracting biological structure from the growing volumes of unlabeled fish imagery.
Declining insect populations make reliable biodiversity monitoring increasingly urgent, yet monitoring of insect biodiversity is hampered by a lack of standardised data and by costly and time-consuming manual identification by expert entomologists. Deep learning-based image classifiers, processing data from automated non-lethal camera traps, have the potential to transform and scale insect biodiversity monitoring. However, challenges remain in acquiring expert-annotated datasets, developing model architectures that generalise well across diverse taxonomic levels and training models on highly imbalanced data. Hierarchical data also benefits from designing models that default to higher-confidence, coarser-level predictions, when uncertain about finer taxonomic levels. In this paper we address these challenges with a deep learning-based hierarchical classification model. First, we present a manually curated, long-tailed dataset of around one million images of insects, extracted from 1,801 camera-trap video recordings and annotated with a five-level, 34-class hierarchy. Further, we adapt a hierarchical classification model architecture to a five-level variable-depth hierarchy, with class-balanced weighting. Our model improves on non-hierarchical classifiers by leveraging biological taxonomy to extract granularity-specific visual features and makes hierarchy-consistent predictions to the deepest taxonomic level that meets a confidence threshold (T = 0.6). Our model achieved a per-level accuracy of 80-99% on test data, across five levels of hierarchy. Furthermore ...
Zaki Mahfoud, Juan A. Chiavassa, Simon Walther et al.· 0 citations
Abstract. Accurate tree species identification is essential for effective forest management, biodiversity monitoring, and resource estimation. While automated methods relying on aerial and canopy-level remote sensing have become prevalent, they often struggle in dense, multi-layered forest stands, where critical lower-stem and bark features are obscured. To address this limitation, we present a Deep Learning (DL) framework for tree species classification utilizing ground-level RGB imagery. Because manual annotation of terrestrial images in forest environments is labor-intensive and complicated by occlusions, we introduce a new “in-situ” forest image dataset alongside an automated labeling pipeline. This pipeline generates training annotations by projecting tree-species data derived from Mobile Laser Scanning (MLS) onto 2D images based on photogrammetric reconstruction. The proposed DL model leverages these automatically labeled images to effectively recognize tree species based on structural and bark characteristics. The model achieves overall F1-scores of 0.78 and 0.75 for object detection and instance segmentation, respectively. Ultimately, our approach complements existing methods for detecting tree positions and diameters, facilitating the creation of a holistic, cost-effective, and scalable forest inventory dataset.
Hristina Hristova, C. Blattert, S. K. P. Kushwaha et al.· The International Archives o...· 0 citations
Distinguishing crop from weed species at the seedling stage is a fine-grained morphological discrimination problem. We study it on the public Plant Seedlings benchmark, which contains twelve species (three crops and nine weeds) imaged at the seedling stage. Automated classifiers report near-ceiling accuracy on this benchmark. Yet its images are acquired in controlled trays containing soil, gravel, rulers, barcodes, and printed labels, so a model may identify a species from its acquisition context rather than its morphology. We audit two architectures, EfficientNet-B7 and ViT-B/16, trained on the V2 dataset (5539 images) and probed with plant-only, background-only, and background-swapped inputs. Near-ceiling models (96.1% and 96.4% over three seeds) recover the correct species for up to 47.7% of samples from the background alone (chance 8.3%) and lose about 60 points under background swapping. Context reliance is therefore a property of the benchmark, not any single architecture. Tracing this to its source, an independent learned representation of the plant-free background alone identifies the species at 72.4%. The reliance is correctable end to end: a consistency-regularisation scheme retains 92.1% full-image accuracy for the transformer with no segmentation at inference, at an architecture-dependent cost. Reported accuracy thus partly measures acquisition context, not morphology; morphological grounding should be measured and reported alongside accuracy.
L. Miloudi, Khaled Rezeg, Mohamed Kotoub Miloudi· International Journal of Pla...· 0 citations
The FathomNetCLEF 2026 competition combines underwater object detection and fine-grained marine species classification under a positive-unlabeled evaluation setting. The provided training labels are sparse, while the hidden test set is out-of-distribution relative to the training imagery, creating both annotation incompleteness and source-shift challenges. We describe DS@GT ARC's multi-stage system developed for this setting while keeping model training restricted to the data provided by the competition. The final private-leaderboard model uses a frozen Megalodon YOLOv8x detector as a class-agnostic proposal generator, combines global and tiled inference with tile-edge filtering, classifies expanded proposal crops with a LoRA-finetuned DINOv3 ViT-H classifier, and ranks predictions using weighted geometric fusion of detector and classifier confidence. This system placed 12th out of 102 teams. A closely related variant added a locally trained TTN-inspired validity head as a light reranking signal, improving public-leaderboard and proxy-evaluation performance but slightly reducing private-leaderboard performance. Across experiments, the strongest lesson was that train-derived validation and detector-only metrics were not reliable enough for model selection. Instead, we used proxy datasets only for validation and comparison, and combined those signals with leaderboard feedback and targeted ablations. These experiments showed that reserving proposal recall, avoiding over-aggressive filtering, and improving downstream ranking were more effective than fine-tuning the detector or directly training on noisy pseudo-labels. Code: https://github.com/dsgt-arc/fathomnetclef-2026.
Robert James Brock, Sebastian Krupa, J. Tam· 0 citations
The core of precision agriculture lies in the effective management of weed growth, a practice that is crucial for achieving maximum crop yield while using only a required amount of herbicides. Although deep learning has improved automation at a high level, a challenge still remains in the area of high performance segmentation models: pixel-level annotations, which are expensive and rarely available in real-world datasets. Addressing this problem, we proposed a weakly supervised design framework to overcome the missing ground-truth segmentation masks. Instead of relying on manual tracing, our approach is made up of a two-stage pipeline using the bounding box annotations to create pseudo-masks with vegetation indices. This innovative idea allows the DeepLabV3+ model to train and learn to distinguish weed structures from complex soil textures and crop backgrounds. In the further stage, the obtained background-suppressed are fed as input into convolutional neural network architectures for species-level classification. The results show that despite the presence of class imbalance problem and high inter-class similarity, the background suppression strategy provides a very high classification accuracy up-to approximately 88%. To validate that model activations align with plant morphological structures such as leaf margins and venation patterns rather than environmental context, gradient-weighted class activation mapping (Grad-CAM) is applied, with quantitative analysis confirming improved morphological focus in segmentation-preprocessed models. Importantly, bounding box annotations are required only during training, at inference time, the pipeline accepts only a raw RGB field image with no annotation input. Finally, this study provides a very cost-effective, end-to-end optimized solution that bridges the gap between coarse, already available datasets and fine-grained precision required for practical field deployment.
Vaibhavv Maheshwari, Shreeya Mohanty, Prakash K. Aithal et al.· IEEE Access· 0 citations
The emergence of Farm Digital Twins (Farm-DT) as a transformative paradigm in smart agriculture demands robust, real-time perception modules capable of continuous plant-level monitoring, predictive analytics, and automated decision support. A critical bottleneck in operationalising Farm-DTs is the absence of interpretable, species-level weed identification engines that can feed spatially precise weed-distribution data into the virtual farm replica for simulation, yield forecasting, and optimized herbicide scheduling. This paper presents a tri-component deep learning framework designed explicitly as a perception and interpretability layer for Farm Digital Twin architectures, evaluated on a five-species balanced subset of the Moving Fields Weed Dataset (MFWD)—a publicly available benchmark of 94K high-resolution images of 28 weed species. Eleven ImageNet pre-trained architectures spanning convolutional neural networks (CNNs) and vision transformers were benchmarked under a unified stratified 80/10/10 holdout protocol. Swin Transformer v1 achieved the highest test accuracy of 97.3% [
F
1
= 0.964; 95% CI: (95.9, 98.4)], and EfficientNetV2-S reached 95.5% [
F
1
=0.956; 95% CI: (93.8, 96.9)]; pairwise McNemar tests confirm these advantages are statistically significant (
p
< 0.01, Bonferroni-corrected). Gradient-weighted Class Activation Mapping (Grad-CAM) applied to the top CNN models confirmed that 94.3% of high-activation pixels overlap with ground-truth foliage annotations, providing quantitative validation that classification decisions are driven by botanically meaningful morphological features. The SegFormer-B3 semantic segmentation module achieved mIoU = 0.8961, enabling precise pixel-level weed delineation that directly populates the DT spatial model for variable-rate herbicide application and robotic weeding simulation. Together, these three components map directly onto the Farm-DT architecture: the classifier feeds the species inventory, the segmentation module populates the spatial weed model, and Grad-CAM provides the trust layer required for agronomist acceptance of DT-automated decisions—collectively advancing real-time monitoring and decision-support for Digital Twin-driven urban and peri-urban agriculture.
A. Manoj, Aiswarya S. Kumar, S. Remya et al.· Frontiers in Sustainable Foo...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
