Stefano Samele

Stefano Samele, Eugenio Lomurno, Teodora Jovanovic et al.

Industrial anomaly detection has historically been a unimodal task. Recent multimodal vision-language models have produced systems that admit textual input alongside the image and are presented as enabling text-guided zero- and few-shot inspection. Yet these methods are evaluated with protocols inherited from unimodal benchmarks that hold the textual condition constant and therefore cannot measure whether language conditions the decision; whether reported gains reflect text guidance or strong pretrained visual features remains open. We introduce Text-Guided Anomaly Detection (TGAD), a structured benchmark that progressively increases the functional role of language across three scenarios: a controlled prompt-sensitivity setting on MVTec AD; a component-tagged extension of MVTec AD that requires the model to restrict its assessment to an instructed part; and the new Assembled Panel Dataset (APD), a realistic industrial setting that requires both defect-type and component-location knowledge. We evaluate one representative model per paradigm: generative large vision-language, training-free discriminative, and embedding-adaptive discriminative. In all three, the textual interface conditions the decision only superficially: prompt content is absorbed unless the object noun is removed (the generative model's I-AUROC drops from 97.4 to 82.6); component-level instructions do not constrain the decision once defects outside the instructed part are admitted as normal (from 90.3 to 66.3); and when both combine on APD, image-level discrimination collapses below the MVTec level, in one case below chance (71.2, 50.5, 31.5). These results suggest that standard benchmarks overstate the text-guided capabilities of current multimodal anomaly detection systems, and that a protocol of this kind is a prerequisite for models that can be reliably controlled through language for industrial deployment.

Andrea Falanti, Eugenio Lomurno, Stefano Samele et al.

Automating the research for the best neural network model is a task that has gained more and more relevance in the last few years. In this context, Neural Architecture Search (NAS) represents the most effective technique whose results rival the state of the art hand-crafted architectures. However, this approach requires a lot of computational capabilities as well as research time, which makes prohibitive its usage in many real-world scenarios. With its sequential model-based optimization strategy, Progressive Neural Architecture Search (PNAS) represents a possible step forward to face this resources issue. Despite the quality of the found network architectures, this technique is still limited in research time. A significant step in this direction has been done by Pareto-Optimal Progressive Neural Architecture Search (POPNAS), which expands PNAS with a time predictor to enable a trade-off between search time and accuracy, considering a multi-objective optimization problem. This paper proposes a new version of the Pareto-Optimal Progressive Neural Architecture Search, called POPNASv2. Our approach enhances its first version and improves its performance. We expanded the search space by adding new operators and improved the quality of both predictors to build more accurate Pareto fronts. Moreover, we introduced cell equivalence checks and enriched the search strategy with an adaptive greedy exploration step. Our efforts allow POPNASv2 to achieve PNAS-like performance with an average 4x factor search time speed-up.

Nico Catalano, Stefano Samele, Paolo Pertino et al.

Few Shot Segmentation aims to segment novel object classes given only a handful of labeled examples, enabling rapid adaptation with minimal supervision. Current literature crucially lacks a selection method that goes beyond visual similarity between the query and example images, leading to suboptimal predictions. We present MARS, a plug-and-play ranking system that leverages multimodal cues to filter and merge mask proposals robustly. Starting from a set of mask predictions for a single query image, we score, filter, and merge them to improve results. Proposals are evaluated using multimodal scores computed at local and global levels. Extensive experiments on COCO-20i, Pascal-5i, LVIS-92i, and FSS-1000 demonstrate that integrating all four scoring components is crucial for robust ranking, validating our contribution. As MARS can be effortlessly integrated with various mask proposal systems, we deploy it across a wide range of top-performer methods and achieve new state-of-the-art results on multiple existing benchmarks. Code will be available upon acceptance.

Eugenio Lomurno, Alberto Archetti, Lorenzo Cazzella et al.

Privacy regulation laws, such as GDPR, impose transparency and security as design pillars for data processing algorithms. In this context, federated learning is one of the most influential frameworks for privacy-preserving distributed machine learning, achieving astounding results in many natural language processing and computer vision tasks. Several federated learning frameworks employ differential privacy to prevent private data leakage to unauthorized parties and malicious attackers. Many studies, however, highlight the vulnerabilities of standard federated learning to poisoning and inference, thus raising concerns about potential risks for sensitive data. To address this issue, we present SGDE, a generative data exchange protocol that improves user security and machine learning performance in a cross-silo federation. The core of SGDE is to share data generators with strong differential privacy guarantees trained on private data instead of communicating explicit gradient information. These generators synthesize an arbitrarily large amount of data that retain the distinctive features of private samples but differ substantially. In this work, SGDE is tested in a cross-silo federated network on images and tabular datasets, exploiting beta-variational autoencoders as data generators. From the results, the inclusion of SGDE turns out to improve task accuracy and fairness, as well as resilience to the most influential attacks on federated learning.