arXiv:2511.15343v1 Announce Type: cross 
Abstract: Developing reliable UAV navigation systems requires robust air-to-air object detectors capable of distinguishing between objects seen during training and previously unseen objects. While many methods address closed-set detection and achieve high-confidence recognition of in-domain (ID) targets, they generally do not tackle open-set detection, which requires simultaneous handling of both ID and out-of-distribution (OOD) objects. Existing open-set approaches typically rely on a single uncertainty score with thresholding, limiting flexibility and often conflating OOD objects with background clutter. In contrast, we propose a lightweight, model-agnostic post-processing framework that explicitly separates background from unknown objects while preserving the base detector's performance. Our approach extends open-set detection beyond binary ID/OOD classification to real-time three-way classification among ID targets, OOD objects, and background. To this end, we employ a fusion scheme that aggregates multiple confidence estimates and per-detection features using a compact multilayer perceptron (MLP). Incorporating different logit variants into the MLP consistently enhances performance across both binary and three-class classification without compromising throughput. Extensive ablation and comparative experiments confirm that our method surpasses threshold-based baselines in two-class classification by an average of 2.7% AUROC, while retaining or improving open-set mAP. Furthermore, our study uniquely enables robust three-class classification, a critical capability for safe UAV navigation, where OOD objects must be actively avoided and background regions safely ignored. Comparative analysis highlights that our method surpasses competitive techniques in AUROC across datasets, while improving closed-set mAP by up to 9 points, an 18% relative gain.

يقدم المقال إطارًا جديدًا للكشف عن الأجسام الجوية يعزز قدرة الطائرات بدون طيار على التمييز بين الأجسام المعروفة وغير المعروفة. على عكس الطرق التقليدية التي تركز على الكشف في مجموعة مغلقة، تتيح هذه الطريقة التصنيف في الوقت الفعلي إلى ثلاث فئات: الأهداف في النطاق (ID)، والأجسام خارج التوزيع (OOD)، والخلفية. تهدف هذه التقنية المعتمدة على ما بعد المعالجة إلى تحسين دقة وموثوقية أنظمة الملاحة للطائرات بدون طيار.

El artículo presenta un nuevo marco para la detección de objetos aéreos que mejora la capacidad de los UAV para distinguir entre objetos conocidos y desconocidos. A diferencia de los métodos tradicionales que se centran en la detección de conjunto cerrado, este enfoque permite la clasificación en tiempo real en tres categorías: objetivos en dominio (ID), objetos fuera de distribución (OOD) y fondo. Esta técnica de post-procesamiento, independiente del modelo, busca mejorar la precisión y fiabilidad de los sistemas de navegación de UAV.

L'article présente un nouveau cadre pour la détection d'objets aériens qui améliore la capacité des UAV à distinguer les objets connus et inconnus. Contrairement aux méthodes traditionnelles qui se concentrent sur la détection en ensemble fermé, cette approche permet une classification en temps réel en trois catégories : cibles en domaine (ID), objets hors distribution (OOD) et arrière-plan. Cette technique de post-traitement, indépendante du modèle, vise à améliorer la précision et la fiabilité des systèmes de navigation UAV.

The article presents a new framework for aerial object detection that enhances the capability of UAVs to distinguish between known and unknown objects. Unlike traditional methods that focus on closed-set detection, this approach enables real-time classification into three categories: in-domain (ID) targets, out-of-distribution (OOD) objects, and background. This model-agnostic post-processing technique aims to improve the accuracy and reliability of UAV navigation systems.

Fast Post-Hoc Confidence Fusion for 3-Class Open-Set Aerial Object Detection

Walmart's early Black Friday deals are here, with big discounts on TVs, laptops, and more (including the lowest-ever prices on AirTags, AirPods, and the Apple Watch Series 10).

Best Walmart Black Friday deals live now: Save up to 60% on Apple, Dyson, TVs, and more

Matter 1.5 may finally fix the biggest headache in buying security cameras - here's how

Organize your workspace with our top picks for the best laptop docking stations available now.

I tested the best laptop docking stations - here's what I recommend for your office setup

Yann LeCun, an artificial intelligence pioneer who runs a research lab at Meta Platforms Inc., told employees that he will depart the social media giant at the end of the year and start a new company, according to a memo obtained by Bloomberg News.

Meta AI pioneer LeCun announces exit, plans new startup

In late September, the German airline Deutsche Lufthansa AG told analysts and investors that it planned to eliminate 4,000 administrative positions by the end of the decade. Among the reasons it cited was "the increased use of artificial intelligence."

Companies are warming up to saying AI is the reason for job cuts

The Xgimi Horizon S Max stands out as one of the brightest and most capable projectors I've tested to date.

Finally, a portable 4K projector worthy of replacing my TV - and it supports Dolby Vision

arXiv:2511.15312v1 Announce Type: new 
Abstract: Unmanned aerial vehicle (UAV) detection and aerial object recognition are critical for modern surveillance and security, prompting a need for robust systems that overcome limitations of single-modality approaches. This research addresses these challenges by designing and rigorously evaluating a novel multimodal Transformer model that integrates diverse data streams: radar, visual band video (RGB), infrared (IR) video, and audio. The architecture effectively fuses distinct features from each modality, leveraging the Transformer's self-attention mechanisms to learn comprehensive, complementary, and highly discriminative representations for classification. The model demonstrated exceptional performance on an independent test set, achieving macro-averaged metrics of 0.9812 accuracy, 0.9873 recall, 0.9787 precision, 0.9826 F1-score, and 0.9954 specificity. Notably, it exhibited particularly high precision and recall in distinguishing drones from other aerial objects. Furthermore, computational analysis confirmed its efficiency, with 1.09 GFLOPs, 1.22 million parameters, and an inference speed of 41.11 FPS, highlighting its suitability for real-time applications. This study presents a significant advancement in aerial object classification, validating the efficacy of multimodal data fusion via a Transformer architecture for achieving state-of-the-art performance, thereby offering a highly accurate and resilient solution for UAV detection and monitoring in complex airspace.

تقدم هذه الدراسة نموذجًا جديدًا متعدد الأنماط من نوع Transformer للكشف عن الطائرات بدون طيار (UAV) والتعرف على الأجسام الجوية، حيث يدمج بيانات الرادار والفيديو RGB والفيديو بالأشعة تحت الحمراء والصوت. يستخدم النموذج آليات الانتباه الذاتي لإنشاء تمثيلات شاملة للتصنيف، محققًا مقاييس أداء عالية، بما في ذلك 0.9812 دقة و0.9954 خصوصية في مجموعة اختبار مستقلة.

Esta investigación presenta un nuevo modelo Transformer multimodal para la detección de vehículos aéreos no tripulados (UAV) y el reconocimiento de objetos aéreos, integrando datos de radar, video RGB, video infrarrojo y audio. El modelo utiliza mecanismos de autoatención para crear representaciones completas para la clasificación, logrando métricas de rendimiento elevadas, incluyendo 0.9812 de precisión y 0.9954 de especificidad en un conjunto de pruebas independiente.

Cette recherche présente un nouveau modèle Transformer multimodal pour la détection de véhicules aériens sans pilote (UAV) et la reconnaissance d'objets aériens, intégrant des données radar, vidéo RGB, vidéo infrarouge et audio. Le modèle utilise des mécanismes d'attention pour créer des représentations complètes pour la classification, atteignant des métriques de performance élevées, y compris 0,9812 de précision et 0,9954 de spécificité sur un ensemble de test indépendant.

This research presents a novel multimodal Transformer model for unmanned aerial vehicle (UAV) detection and aerial object recognition, integrating radar, RGB video, infrared video, and audio data. The model utilizes self-attention mechanisms to create comprehensive representations for classification, achieving high performance metrics, including 0.9812 accuracy and 0.9954 specificity on an independent test set.

A Multimodal Transformer Approach for UAV Detection and Aerial Object Recognition Using Radar, Audio, and Video Data

arXiv:2511.13924v1 Announce Type: new 
Abstract: Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned CoT reasoning can paradoxically degrade performance in Visual Grounding tasks, particularly as CoT outputs become lengthy or complex. Additionally, our analysis reveals that increased dataset size does not always enhance performance due to varying data complexities. Motivated by these findings, we propose Curriculum-based Relative Policy Optimization (CuRPO), a novel training strategy that leverages CoT length and generalized Intersection over Union (gIoU) rewards as complexity indicators to progressively structure training data from simpler to more challenging examples. Extensive experiments on RefCOCO, RefCOCO+, RefCOCOg, and LISA datasets demonstrate the effectiveness of our approach. CuRPO consistently outperforms existing methods, including Visual-RFT, with notable improvements of up to +12.52 mAP on RefCOCO. Moreover, CuRPO exhibits exceptional efficiency and robustness, delivering strong localization performance even in few-shot learning scenarios, particularly benefiting tasks characterized by ambiguous and intricate textual descriptions.The code is released on https://github.com/qyoung-yan/CuRPO.

يقدم المقال استراتيجية تدريب جديدة تُسمى تحسين السياسة النسبية القائمة على المنهج (CuRPO) تهدف إلى تحسين مهام التوجيه البصري. يسلط الضوء على قيود تحفيز سلسلة التفكير (CoT)، خاصة عندما تصبح المخرجات طويلة أو معقدة، مما قد يؤدي إلى تدهور الأداء. تكشف الدراسة أن زيادة حجم مجموعة البيانات لا يضمن دائمًا تحسين النتائج بسبب تعقيدات البيانات المتنوعة. يستخدم CuRPO طول CoT ومكافآت التقاطع العام (gIoU) كدلائل على التعقيد لتنظيم بيانات التدريب تدريجيًا من أمثلة أبسط إلى أكثر تحديًا، مما يظهر فعالية نهجنا عبر عدة مجموعات بيانات.

El artículo presenta una nueva estrategia de entrenamiento llamada Optimización de Política Relativa Basada en el Currículo (CuRPO) destinada a mejorar las tareas de Visual Grounding. Destaca las limitaciones del prompting de Cadena de Pensamiento (CoT), especialmente cuando las salidas se vuelven largas o complejas, lo que puede degradar el rendimiento. El estudio revela que aumentar simplemente el tamaño del conjunto de datos no garantiza mejores resultados debido a las complejidades variables. CuRPO utiliza la longitud de CoT y las recompensas de Intersección Generalizada sobre la Unión (gI…

L'article présente une nouvelle stratégie de formation appelée Optimisation de Politique Relative Basée sur le Curriculum (CuRPO) visant à améliorer les tâches de Visual Grounding. Il met en évidence les limites du prompting Chain-of-Thought (CoT), en particulier lorsque les sorties deviennent longues ou complexes, ce qui peut dégrader les performances. L'étude révèle qu'augmenter simplement la taille du jeu de données ne garantit pas de meilleurs résultats en raison des complexités variées. CuRPO utilise la longueur de CoT et les récompenses d'Intersection Généralisée sur l'Union (gIoU) pour …

The article presents a novel training strategy called Curriculum-based Relative Policy Optimization (CuRPO) aimed at improving Visual Grounding tasks. It highlights the limitations of Chain-of-Thought (CoT) prompting, particularly when outputs become lengthy or complex, which can degrade performance. The study reveals that simply increasing dataset size does not guarantee better results due to varying complexities. CuRPO utilizes CoT length and generalized Intersection over Union (gIoU) rewards to structure training data progressively from simpler to more challenging examples, demonstrating ef…

Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding

arXiv:2509.22855v3 Announce Type: replace 
Abstract: Online learning to rank (OLTR) plays a critical role in information retrieval and machine learning systems, with a wide range of applications in search engines and content recommenders. However, despite their extensive adoption, the susceptibility of OLTR algorithms to coordinated adversarial attacks remains poorly understood. In this work, we present a novel framework for attacking some of the widely used OLTR algorithms. Our framework is designed to promote a set of target items so that they appear in the list of top-K recommendations for T - o(T) rounds, while simultaneously inducing linear regret in the learning algorithm. We propose two novel attack strategies: CascadeOFA for CascadeUCB1 and PBMOFA for PBM-UCB . We provide theoretical guarantees showing that both strategies require only O(log T) manipulations to succeed. Additionally, we supplement our theoretical analysis with empirical results on real-world data.

Observation-Free Attacks on Online Learning to Rank

arXiv:2511.15406v1 Announce Type: cross 
Abstract: Reliable semantic segmentation is essential for clinical decision making, yet deep models rarely provide explicit statistical guarantees on their errors. We introduce a simple post-hoc framework that constructs confidence masks with distribution-free, image-level control of false-positive predictions. Given any pretrained segmentation model, we define a nested family of shrunken masks obtained either by increasing the score threshold or by applying morphological erosion. A labeled calibration set is used to select a single shrink parameter via conformal prediction, ensuring that, for new images that are exchangeable with the calibration data, the proportion of false positives retained in the confidence mask stays below a user-specified tolerance with high probability. The method is model-agnostic, requires no retraining, and provides finite-sample guarantees regardless of the underlying predictor. Experiments on a polyp-segmentation benchmark demonstrate target-level empirical validity. Our framework enables practical, risk-aware segmentation in settings where over-segmentation can have clinical consequences. Code at https://github.com/deel-ai-papers/conseco.

تم تقديم إطار عمل جديد للتحكم في الإيجابيات الكاذبة في تقسيم الصور، مما يعزز موثوقية التقسيم الدلالي في اتخاذ القرارات السريرية. تستخدم هذه الطريقة المستقلة عن النموذج التنبؤ المتوافق لإنشاء أقنعة ثقة تحافظ على مستوى محدد مسبقًا من الإيجابيات الكاذبة، دون الحاجة إلى إعادة التدريب. تُظهر الطريقة ضمانات عالية الاحتمالية للصور الجديدة، مما يمثل تقدمًا كبيرًا في التصوير الطبي.

Se ha introducido un nuevo marco para controlar los falsos positivos en la segmentación de imágenes, mejorando la fiabilidad de la segmentación semántica en la toma de decisiones clínicas. Este enfoque independiente del modelo utiliza la predicción conformal para crear máscaras de confianza que mantienen una tolerancia definida por el usuario para los falsos positivos, sin necesidad de reentrenamiento. El método demuestra garantías de alta probabilidad para nuevas imágenes, representando un avance significativo en la imagen médica.

Un nouveau cadre pour contrôler les faux positifs dans la segmentation d'images a été introduit, améliorant la fiabilité de la segmentation sémantique dans la prise de décision clinique. Cette approche indépendante du modèle utilise la prédiction conforme pour créer des masques de confiance qui maintiennent une tolérance définie par l'utilisateur pour les faux positifs, sans nécessiter de réentraînement. La méthode démontre des garanties de haute probabilité pour de nouvelles images, représentant une avancée significative dans l'imagerie médicale.

A new framework for controlling false positives in image segmentation has been introduced, enhancing the reliability of semantic segmentation in clinical decision-making. This model-agnostic approach utilizes conformal prediction to create confidence masks that maintain a user-defined tolerance for false positives, without requiring retraining. The method demonstrates high probability guarantees for new images, making it a significant advancement in medical imaging.

Controlling False Positives in Image Segmentation via Conformal Prediction

arXiv:2409.13566v3 Announce Type: replace 
Abstract: The application of TensorFlow pre-trained models in deep learning is explored, with an emphasis on practical guidance for tasks such as image classification and object detection. The study covers modern architectures, including ResNet, MobileNet, and EfficientNet, and demonstrates the effectiveness of transfer learning through real-world examples and experiments. A comparison of linear probing and model fine-tuning is presented, supplemented by visualizations using techniques like PCA, t-SNE, and UMAP, allowing for an intuitive understanding of the impact of these approaches. The work provides complete example code and step-by-step instructions, offering valuable insights for both beginners and advanced users. By integrating theoretical concepts with hands-on practice, the paper equips readers with the tools necessary to address deep learning challenges efficiently.

Fast Post-Hoc Confidence Fusion for 3-Class Open-Set Aerial Object Detection

Was this article worth reading? Share it