The core problem the researchers tackled is twofold. First, conventional intrusion detection systems rely on enormous, carefully labeled datasets of network traffic. In IoT settings, such datasets are nearly impossible to assemble, because privacy concerns, thin monitoring infrastructure, and the sheer cost of manual annotation get in the way. Second, even the newer generation of few-shot learning systems, which are designed to learn from scarce data, turn out to be exquisitely vulnerable to adversarial examples: inputs that have been nudged by tiny, mathematically optimized perturbations designed to push them across a classifier’s decision boundary. A model can look brilliant on clean traffic and collapse catastrophically the moment an adversary bends it.

The team’s answer, which they call Adv-ProtoNet, fuses two ideas that had previously lived separate lives. The first is a Prototypical Network, a metric-based few-shot learning architecture. Instead of memorizing decision boundaries from millions of samples, the network learns an embedding function that maps network traffic into a space where each class of traffic, benign or malicious, is represented by a prototype, essentially the center of mass of its few labeled examples. A new packet is classified by measuring its squared Euclidean distance to each prototype and applying a softmax over those distances. The second idea is adversarial training, in which the model is deliberately attacked during training with perturbed versions of its own data so that it learns to withstand such attacks in the wild.

The integration is formulated as a min-max optimization problem. In the inner loop, the system generates the worst-case perturbation it can within a small, norm-bounded ball around each query sample, using one of four canonical gradient-based attacks: the Fast Gradient Sign Method (FGSM), the optimization-based Carlini and Wagner (C&W) attack, the boundary-seeking DeepFool, and the iterative Projected Gradient Descent (PGD), widely regarded as the gold-standard benchmark for first-order adversaries. In the outer loop, the network minimizes a weighted sum of the standard few-shot loss and the adversarial loss, with a hyperparameter lambda balancing clean accuracy against robustness. The effect, the authors explain, is to enforce local smoothness in the embedding space: small perturbations no longer drag a sample away from its true class prototype, so the entire neighborhood around each example remains inside the correct decision region.

Importantly, the researchers evaluated their system under a strict white-box threat model, the most pessimistic assumption possible. The adversary is assumed to know the model’s architecture, its feature representation, and its internal weights, and can therefore compute full gradients to craft highly optimized attacks. The security goals were correspondingly framed as worst-case guarantees against first-order adversaries. This is a deliberately conservative choice; a system that survives white-box attacks is far harder to defeat in the messier, information-poor conditions of a real network.

The experimental stage was the IDSIoT2024 dataset, a large and recent collection of more than 16 million network traffic samples spanning 96 features and seven classes: benign traffic plus six attack categories, including denial of service, injection, man-in-the-middle, malware, routing, and vulnerability analysis. The data was standardized to zero mean and unit variance, then split into 64 percent training, 16 percent validation, and 20 percent testing subsets with a fixed random seed to prevent leakage. Training followed an episodic protocol: across 5,000 episodes, each task sampled all seven classes with just three support examples per class to build the prototypes and five query examples to compute the loss. This three-shot regime deliberately mimics the data poverty of real IoT deployments.

Under benign conditions, the framework performed impressively. The baseline Prototypical Network achieved a mean accuracy of 93.83 percent, with precision at 93.72 percent and an F1-score of 93.75 percent. The class-wise picture was even more striking: the model correctly identified 99 percent of denial of service attacks and a perfect 100 percent of man-in-the-middle, malware, and routing attacks, with only the injection class lagging at 80 percent detection. For a system that never saw more than three labeled examples per class, this is a strong demonstration that metric learning can anchor reliable class prototypes even in extremely low-data regimes.

Then came the adversarial stress tests, and the initial results were sobering. Without adversarial training, accuracy collapsed to 11.43 percent under FGSM, 14.23 percent under C&W, 14.23 percent under DeepFool, and 14.46 percent under PGD, a near-random level of performance that shows how thoroughly perturbations scrambled the distance relationships in the embedding space. After integrating each attack into the episodic training loop, however, the picture transformed. Accuracy recovered to 86.57 percent against FGSM, 87.43 percent against C&W, 87.83 percent against PGD, and a remarkable 94.97 percent against DeepFool, effectively matching the clean baseline. The confusion matrices confirmed the recovery, with true-positive diagonals restored and class accuracies returning to 100 percent for several attack types under the DeepFool scenario.

Ablation studies and comparisons sharpened the message. A standard deep neural network, despite reaching 93.66 percent on clean data, fell to between roughly 43 and 51 percent under attack. A standard Prototypical Network did even better on clean data at 94.69 percent but collapsed to between 20 and 29 percent under adversarial pressure, proving that metric learning alone offers no immunity. Only the hybrid Adv-ProtoNet, trading a few points of clean accuracy for consistent robustness in the 78 to 83 percent range across all four attacks, held the line. Classical baselines constrained to the same three-shot regime fared far worse on clean data, with a support vector machine managing just 55.94 percent and a random forest 74.69 percent, compared with 95.71 percent for the standard ProtoNet. Matching Networks and Relation Networks, other state-of-the-art few-shot methods, matched or exceeded the clean accuracy of the proposed model but crumbled under PGD to below 21 percent, leaving Adv-ProtoNet as the only framework in the comparison that survived the full adversarial gauntlet.

Just as important for real-world deployment is the computational profile. The framework’s memory footprint stays between roughly 20 and 20.4 megabytes even with adversarial optimization enabled, because the perturbation generation reuses existing computational graph allocations. Meta-training, which takes between about 32 and 182 seconds depending on the attack, runs offline on centralized hardware, so the burden never touches the IoT edge. Inference is the critical metric for live defense, and here the numbers are compelling: standard queries are classified in 0.06 to 0.09 milliseconds, and even the heaviest adversarial evaluation stays under one millisecond. The authors caution that future work must extend the approach to black-box and transfer-based attacks and to lightweight adaptations for real-time edge deployment, but the study makes a persuasive case that the dual challenges of data scarcity and adversarial vulnerability in IoT security are not separate problems to be solved in isolation. They are, it turns out, best solved together, by teaching a model to recognize attacks from almost nothing and to hold its ground when those attacks fight back.

Subject of Research: Adversarially robust few-shot learning for intrusion detection in Internet of Things networks

Article Title: Adversarially robust few-shot learning for aI-enabled attack mitigation in the internet of things

Article References: Asiri, F., Alturki, N., Alnazzawi, N., Khattak, A. A., Ali, H., Naeem, U., & Latif, S. (2026). Adversarially robust few-shot learning for aI-enabled attack mitigation in the internet of things. Cluster Computing, 29(12), Article 731. https://doi.org/10.1007/s10586-026-06528-5

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06528-5

Keywords: Internet of Things, few-shot learning, adversarial training, intrusion detection, prototypical networks, cybersecurity, machine learning, adversarial attacks, FGSM, PGD, network security, resource-constrained devices

The research, led by JiaLi Zhou and colleagues at Zhongshan Hospital of Xiamen University in China, tackled a problem that has long frustrated the application of deep learning to medicine: the scarcity of expertly labeled data. Standard supervised learning algorithms generally require thousands of examples to learn reliably, but assembling large cohorts of newly diagnosed Crohn’s disease patients with consensus severity grades from multiple specialists is expensive, slow, and often impractical in a single center. The team’s solution was to turn to few-shot learning, a family of techniques specifically designed to extract maximum signal from minimal labeled data.

The study drew on the electronic medical records of 106 patients with newly diagnosed Crohn’s disease treated at Zhongshan Hospital. For each patient, a panel of experts produced a consensus severity classification, which served as the reference standard the algorithms would attempt to reproduce. Rather than treating severity as a single continuous score, the framework aimed to replicate the categorical stratification that expert consensus produces, effectively teaching a machine to mimic the collective judgment of experienced clinicians at the moment of diagnosis.

Three distinct few-shot learning architectures were built and compared. The first was a metric learning approach, which trains a model to map patient records into a mathematical space where similar cases land close together and dissimilar cases land far apart. The second, matching networks, extends this idea by comparing each new patient against a small set of labeled examples at prediction time, weighing the evidence from each comparison. The third, and ultimately the star of the study, was the prototypical network, which computes a representative prototype, essentially an average embedding, for each severity class and then classifies new patients by measuring which prototype they most resemble. This approach is elegant in its simplicity: instead of memorizing individual cases, the model learns a compact summary of what mild, moderate, and severe disease each look like in the data.

To evaluate the models rigorously, the researchers employed nested cross-validation, a demanding scheme in which model selection and performance estimation are kept separate to avoid optimistic bias. For standardized comparison, each trained feature embedding backbone was followed by a logistic regression classifier fitted on training-set embeddings and applied to the corresponding validation fold. Performance was measured using accuracy, macro-F1 score, and the area under the receiver operating characteristic curve, or AUC, across different combinations of input features. The prototypical network emerged as the strongest performer, achieving a mean macro-F1 of 0.817, narrowly ahead of matching networks at 0.812 and metric learning at 0.796. Given the modest size of the dataset, the consistency of these results across architectures is itself noteworthy, suggesting that the underlying clinical features carry genuine, learnable structure related to severity.

One of the most important contributions of the study lies in its commitment to interpretability. Black-box predictions are a hard sell in clinical medicine, where physicians need to understand why a model assigns a particular grade before trusting it. The researchers applied SHAP, or SHapley Additive exPlanations, a technique borrowed from cooperative game theory that assigns each input feature a quantitative contribution to every individual prediction. Combined with Pearson correlation analysis, the SHAP framework identified which clinical variables drove the severity classifications, giving clinicians a window into the model’s reasoning rather than forcing them to accept its verdicts on faith.

The team also probed how much the model depended on cross-sectional imaging. CT enterography, or CTE, provides detailed structural information about the bowel wall and surrounding tissues, and it is a cornerstone of severity assessment in Crohn’s disease. In a feature-ablation analysis centered on the prototypical network, the researchers removed the CTE-derived features and re-evaluated performance in a temporally independent validation cohort of 23 patients, meaning patients diagnosed after the model development period. The results were revealing: the model retained acceptable AUCs for classifying mild and moderate disease without imaging data, but the AUC for the severe class dropped to 0.842. The message is clear that structural information from cross-sectional imaging remains particularly important for recognizing severe disease, precisely the category where treatment decisions are most consequential.

The authors are candid about the limitations of their work, and this transparency matters for how the findings should be interpreted. Because some of the same clinical information that informed the expert consensus labels also served as model predictors, the performance estimates are subject to incorporation bias. In other words, the model is, to some extent, learning to reproduce the inputs that experts themselves weighed, rather than discovering entirely independent markers of severity. The validation cohort of 23 patients is also small, and the study was conducted at a single center, raising questions about how well the framework would generalize to populations with different demographics, care pathways, or data recording practices.

Despite these caveats, the study represents a meaningful proof of concept for a scenario that is increasingly common in clinical machine learning: the expert-labeled dataset that is too small for conventional deep learning but too valuable to ignore. Few-shot learning offers a principled middle path, leveraging metric-space reasoning and prototype construction to squeeze reliable classification out of dozens rather than thousands of cases. If larger, multicenter, and fully independent validations confirm these preliminary results, the framework could evolve into a decision-support tool that standardizes baseline risk stratification at diagnosis, helping to ensure that patients with severe Crohn’s disease are identified and treated aggressively from the outset, regardless of which clinician first evaluates them.

The work also highlights a broader trend in translational medicine, where the bottleneck is shifting from algorithmic capability to the quality and consistency of clinical reference standards. Expert consensus labels are the gold standard by necessity, but they are labor-intensive and inherently subjective at the margins. A machine learning framework that can approximate that consensus reliably, and explain its reasoning through tools like SHAP, could eventually help harmonize severity assessment across centers, making clinical trials more comparable and everyday care more consistent. For now, the Xiamen team’s prototypical network remains a promising prototype in its own right, awaiting the larger independent cohorts that will determine whether it can move from retrospective analysis to the clinic.

Subject of Research: Few-shot machine learning for expert-consensus severity stratification in newly diagnosed Crohn's disease

Article Title: Few-shot learning for expert consensus severity stratification in newly diagnosed crohn’s disease

Article References: Zhou, J., Chen, Y., Chen, Y., Bao, J., Xu, J., Deng, L., Hu, Y., & Dong, J. (2026). Few-shot learning for expert consensus severity stratification in newly diagnosed crohn’s disease. Journal of Translational Medicine. https://doi.org/10.1186/s12967-026-09041-w

Image Credits: AI Generated

DOI: 10.1186/s12967-026-09041-w

Keywords: few-shot learning, Crohn's disease, machine learning, electronic medical records, prototypical networks, severity stratification, inflammatory bowel disease, SHAP interpretability, CT enterography, clinical decision support, nested cross-validation, predictive markers

The challenge the team set out to solve is rooted in the architecture of the Internet of Things itself. Smart cities, factories, hospitals, and homes now host billions of connected sensors, cameras, controllers, and industrial instruments, each producing its own distinctive stream of network traffic. A security model trained on data from one site often fails dismally when deployed at another, because the statistical distribution of traffic differs from client to client. Machine learning researchers call this non-independent and non-identically distributed data, or non-IID data for short, and it is the bane of federated learning, the technique in which many devices collaboratively train a shared model by exchanging only model updates rather than raw records. Centralized intrusion detection systems, meanwhile, raise privacy concerns because they require collecting sensitive network logs in one location, and they generalize poorly across domains.

FedCAMP-IDS answers these problems with a layered design that combines several ideas from the frontiers of machine learning into one federated pipeline. The first stage is what the authors call Cluster-Aware Contrastive Pretraining, or CACP. Before the network ever learns to classify traffic as benign or malicious, it groups similar traffic patterns using K-means clustering and then applies a contrastive optimization objective guided by cosine similarity. In plain terms, the model is rewarded for pulling representations of similar network behavior closer together in its internal embedding space while pushing dissimilar behavior apart. This produces compact, consistent embeddings that remain comparable across clients even when each client sees a very different slice of the network world, which is precisely the condition that breaks most federated systems.

The second pillar of the framework is a memory-augmented prototypical network, a class of model built for few-shot learning, meaning it can learn to recognize attack categories from only a handful of examples. Prototypical networks work by computing a representative vector, or prototype, for each class of traffic and then classifying new samples by measuring their distance to those prototypes. FedCAMP-IDS enhances this mechanism with an external memory module and an adaptive prototype mixing and refinement procedure, allowing each participating device to personalize its prototypes to local conditions while still benefiting from the collective knowledge of the federation. Because the prototypes, rather than entire datasets or full models, are what get shared, the communication burden stays light and the memory footprint remains bounded, two properties the authors highlight as essential for deployment on resource-constrained IoT infrastructure.

Perhaps the most consequential feature for real-world defenders is the framework’s approach to the unknown. Most intrusion detectors are closed-set classifiers: they can only assign traffic to the attack categories they were trained on. A genuinely novel exploit, a zero-day attack, or an out-of-distribution anomaly simply gets forced into the nearest familiar bucket, often labeled as benign. FedCAMP-IDS incorporates open-set recognition based on Extreme Value Theory, a statistical framework for modeling the tails of probability distributions. By calibrating how extreme a sample’s distance from known prototypes is, the system can flag traffic that does not belong to any known class as suspicious without retraining the model. The authors report that this EVT-based calibration enabled robust detection of zero-day and anomalous attacks across their experiments, a capability that could buy network operators precious time when facing adversaries wielding techniques no dataset has ever recorded.

To test the framework, the team ran comprehensive experiments in a distributed federated setting using five widely used benchmark datasets: UNSW-NB15, Bot-IoT, ToN-IoT, CICIDS2018, and NF-UQ-NIDS-v2. These datasets collectively span consumer IoT botnets, industrial telemetry, enterprise network attacks, and modern flow-based traffic captures, giving the evaluation a breadth that mirrors the heterogeneity of real deployments. The results were striking. FedCAMP-IDS achieved up to 99.16 percent accuracy, a 98.53 percent F1-score, and 98.57 percent AUROC, a measure of the model’s ability to separate malicious from benign traffic across all decision thresholds. Against existing federated intrusion detection baselines, the system outperformed by up to 5.7 percentage points in heterogeneous environments, the very settings where competing approaches tend to falter.

Even more telling was the framework’s performance under blind cross-dataset evaluation, a brutal test in which a model trained on one dataset is unleashed on an entirely different one it has never seen. Without any additional retraining, FedCAMP-IDS maintained an average accuracy of 82.5 percent across these cross-domain trials. That figure signals strong generalization and open-set robustness, suggesting the learned representations capture fundamental structure in network behavior rather than overfitting to the quirks of a particular capture environment. For security teams, this kind of transferability matters enormously, because attackers do not respect the boundaries between datasets, vendors, or network segments, and retraining models from scratch for every new deployment is rarely feasible at scale.

The design choices also carry practical weight for the economics of deployment. Federated learning systems can choke on communication costs when they require frequent exchange of large model updates among thousands of devices. FedCAMP-IDS sidesteps this with a lightweight prototype-sharing strategy and a bounded-memory design, which the authors say reduces both communication and storage overhead enough to make the framework suitable for scalable rollout in smart-city, enterprise, and industrial IoT infrastructures. The work forms part of the Blockchain Technology Research Group, known as BTrust Lab, at ABV-IIITM Gwalior, and the authors note that the study received no external funding and that they declare no competing interests.

The study arrives amid a wave of research into federated and privacy-preserving intrusion detection, with recent efforts exploring graph-based clustering for aggregation, personalized federated learning, knowledge distillation, contrastive federated approaches, and few-shot self-supervised frameworks for IoT defense. Against that backdrop, FedCAMP-IDS distinguishes itself by unifying pretraining, few-shot prototypical learning, personalization, and open-set recognition in a single architecture rather than treating them as separate problems. If its reported numbers hold up in field deployments, the framework could offer a template for securing the next generation of connected infrastructure, one in which devices learn collectively to defend themselves without ever surrendering the sensitive traffic data that makes them vulnerable in the first place.

Subject of Research: Privacy-preserving federated learning for intrusion detection in heterogeneous IoT environments

Article Title: FedCAMP-IDS: a federated cluster-aware memory-augmented prototypical network for intrusion detection in heterogeneous IoT environments

Article References: Yadav, A. S., Pawar, V., & Yadav, R. (2026). FedCAMP-IDS: a federated cluster-aware memory-augmented prototypical network for intrusion detection in heterogeneous IoT environments. Cluster Computing, 29(14), Article 794. https://doi.org/10.1007/s10586-026-06538-3

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06538-3

Keywords: intrusion detection, federated learning, IoT security, prototypical networks, contrastive learning, zero-day attacks, open-set recognition, extreme value theory, few-shot learning, cybersecurity, non-IID data, smart cities

The problem the researchers set out to solve is known as few-shot fine-grained image classification. Fine-grained classification refers to tasks where the categories differ only in subtle visual details, such as the wing markings that separate two nearly identical bird species, the grille shape that distinguishes one car model from another, or the muzzle proportions that differentiate closely related dog breeds. Few-shot learning adds a second layer of difficulty: the model must learn to recognize new categories from only one or five labeled examples, called support samples, rather than the thousands typically used in modern deep learning. Under these extreme constraints, standard training procedures often fail in a characteristic way. Instead of learning the meaningful semantic features that define a category, the network latches onto spurious background details, lighting conditions, or incidental textures that happen to correlate with the few examples it has seen. This overfitting severely limits generalization to new, unseen images.

Prototypical networks, first introduced by Snell and colleagues in 2017, remain one of the most popular foundations for few-shot learning. The idea is elegant: for each class, the network computes a prototype, essentially an average of the feature embeddings of the support examples, and then classifies a query image by measuring which prototype lies closest to the query’s embedding in feature space. The approach is simple, fast, and effective, but its Achilles heel is the quality of the embeddings themselves. When support sets are tiny, the prototypes are computed from very few points, and if those embeddings are noisy or dominated by irrelevant visual information, the entire classification scheme collapses. Previous efforts to strengthen prototypical networks for fine-grained tasks have explored part-level contrastive learning, trilinear spatial-awareness modules, bi-similarity networks, and attention-based meta learning, all attempting to force the encoder to focus on the discriminative regions that actually separate similar categories.

DiffProNet takes a different route, one inspired by the mathematics of diffusion models. Diffusion models, which power many of today’s most impressive image generators, work by gradually adding Gaussian noise to data and then training a network to reverse the process, predicting and removing the noise step by step. The Applied Intelligence team realized that the denoising objective itself, separate from any image generation, could serve as a self-supervised training signal. Rather than corrupting pixels, DiffProNet injects Gaussian noise directly into the support feature representations produced by the encoder. A dedicated component, called the Feature Denoising Head, is then trained to predict exactly which noise was injected. Because the network knows the ground-truth noise it added, this becomes a self-supervised auxiliary objective requiring no additional labels whatsoever.

The effect of this denoising task on the learning pipeline is subtle but significant. To predict injected noise accurately, the encoder must produce feature representations that are smooth, structured, and informative enough that the noise signal can be disentangled from the underlying semantic content. In practice, this pressure encourages the encoder to learn robust and discriminative features rather than memorizing the quirks of individual support images. The researchers describe the mechanism as regularizing the latent feature space: the denoising objective spreads the learned representations in a way that mitigates overfitting to irrelevant visual details. In other words, the network is forced to keep its internal geometry clean, and a clean geometry makes the prototype-based classification of query images far more reliable when only one or five examples define each class.

Importantly, the authors emphasize that DiffProNet does not perform image generation at all. This distinction matters both conceptually and computationally. Full diffusion models require many iterative denoising steps to synthesize an image, making them expensive to run. By operating entirely in feature space and using the diffusion-inspired objective only as an auxiliary training signal, DiffProNet captures the regularizing benefit of the denoising principle while keeping the few-shot classification pipeline lightweight. The Feature Denoising Head adds a modest amount of architecture, but the core classification mechanism remains the familiar prototype comparison, preserving the simplicity that has made prototypical networks a mainstay of the field.

To evaluate the framework, the team ran extensive experiments on three of the most widely used fine-grained benchmarks in computer vision. CUB-200-2011, developed by Wah and colleagues, contains roughly 12,000 images spanning 200 species of birds, and is famous for demanding attention to minute plumage and morphological differences. Stanford Dogs, introduced by Khosla and colleagues, covers 120 dog breeds with visually overlapping characteristics. Stanford Cars, from Krause and colleagues, includes 196 makes and models of vehicles where distinctions often hinge on small details of trim, badges, and body shape. Across all three datasets, DiffProNet delivered competitive performance in both the 1-shot setting, where a single example defines each new class, and the 5-shot setting, which offers slightly more support data. The consistency across datasets with very different subject matter suggests that feature-space denoising is a general-purpose remedy for the overfitting that plagues few-shot fine-grained recognition, rather than a trick tailored to one domain.

The study also situates itself within a broader wave of research connecting self-supervised learning to few-shot classification. Earlier work by members of the same team, including self-supervised contrastive learning approaches and the SSL-ProtoNet framework, showed that auxiliary self-supervised tasks can substantially improve few-shot performance. Other groups have pursued related directions, such as self-supervised knowledge distillation, reinforced self-supervised training, and progressive dual-domain feature fusion. DiffProNet extends this lineage by importing the denoising principle from diffusion models, a family of techniques that had previously been applied mainly to generative tasks. The result is a hybrid: the metric-based simplicity of prototypical networks, the label-free training signal of self-supervision, and the noise-prediction mathematics of diffusion, all combined into a single framework that can be trained end to end.

The practical implications reach well beyond benchmark leaderboards. Fine-grained recognition with minimal labeled data is exactly the situation faced in many real-world applications: identifying endangered species from camera-trap photos where only a few verified images exist, detecting rare manufacturing defects on production lines, cataloging newly discovered specimens in biodiversity surveys, or assisting medical specialists who can only annotate a small number of cases. In each of these settings, collecting large labeled datasets is expensive or impossible, and models that overfit to backgrounds or incidental details produce unreliable predictions. A regularizer that improves the robustness of learned features without requiring extra labels could therefore translate directly into more dependable systems in the field.

The researchers have released their source code and experimental configurations in a public GitHub repository, along with instructions for obtaining and preparing the three benchmark datasets, allowing other teams to reproduce and build on the results. The work was supported by the Fundamental Research Grant Scheme of the Malaysian Ministry of Higher Education, awarded to Multimedia University. As diffusion models continue to dominate headlines for their generative prowess, DiffProNet offers a reminder that the ideas behind them can be even more versatile than the images they produce. By teaching a network to find its way back from noise, the researchers have shown that sometimes the best way to help a model see clearly is to first let it practice un-blurring its own view of the world, one feature at a time.

Subject of Research: Few-shot fine-grained image classification using diffusion-inspired feature-space denoising in prototypical networks

Article Title: Diffusion-inspired prototypical network for few-shot fine-grained classification

Article References: Lim, J. M., Lim, K. M., Goh, P. Y., & Lee, C. P. (2026). Diffusion-inspired prototypical network for few-shot fine-grained classification. Applied Intelligence, 56(15), Article 471. https://doi.org/10.1007/s10489-026-07509-2

Image Credits: AI Generated

DOI: 10.1007/s10489-026-07509-2

Keywords: few-shot learning, fine-grained classification, prototypical networks, diffusion models, self-supervised learning, feature denoising, computer vision, machine learning, CUB-200-2011, Stanford Dogs, Stanford Cars, Applied Intelligence