As a critical application of computational intelligence in remote sensing, deep learning-based synthetic aperture radar (SAR) image target recognition facilitates intelligent perception but typically relies on centralized training, where multi-source SAR data are uploaded to a single server, raising privacy and securit...
Yuchao Hou (Shanxi Normal University, Taiyuan, China) et al.· 0 citations
Continual learning (CL) evaluates adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they acquire new ones. While numerous solutions have been proposed, existing experimental setups often r...
Nadia Nasri, Carlos Guti\'errez-\'Alvarez, Sergio Lafuente-Arroyo et al.· 0 citations
Numerical results with early-exit MobileNetV2 and ShuffleNetV2 demonstrate near-perfect UE fairness with aggregate utility close to a Sum-Utility benchmark, reveal security-induced resource fragmentation, and demonstrate the Stage-A scalability from 6 to 144 UEs with median solving time below 0.1~s.
This work systematically sparsify SparseTalk's semantic embeddings, including the previously underexplored regime below a single image-equivalent block down to 8 visual tokens, and introduces an object-based sparsification method that distributes the token budget across detected object instances while retaining backgro...
Davit Soselia, J. Jaja, Amitabh Varshney· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which task models are fine-tuned. We contribute a systematic design for production. Requirements and pass marks were fixed before any run, eight candidates screened under pre-r...
In-context learning (ICL) enables models to infer tasks from demonstrations, but existing benchmarks generally lack matched text and image versions needed to compare ICL performance across modalities. We introduce TwinICL, a procedurally generated benchmark providing such pairs for controlled comparison. Across six ope...
Zihan Xue, Po-Yi Lu, Serhii Honcharenko et al.· 0 citations
This work proposes a self-supervised Track-Any-Point approach that learns from unlabeled surgical videos by establishing global pixel correspondences and inferring point trajectories through contrastive random walks, and achieves performance comparable to existing semi-supervised approaches while implicitly handling ti...
Jiaming Zhang, Zi-Jian Wu, Mehran Armand et al.· Proceedings of the Hamlyn Sy...· 0 citations
Bird-strike mitigation at wind farms requires identifying distant birds that span only tens of pixels, so the classifier's input resolution N is a design variable, not a fixed specification. We study it with a factorial design over 14 side lengths N (16 to 224), six architectures, two training and evaluation regimes an...
An attention-enhanced Transformer framework for ASD classification, evaluated on two structurally different 3D gait feature representations: precomputed statistical gait descriptors and raw biomechanical ground-reaction- force measurements.
M. Mahamood, M. Shahriar, Mridul Sikder et al.· 0 citations
Subtomogram classification in cryo-electron tomography (cryo-ET) is a challenging problem due to the scarcity of labeled examples. While cryo-ET simulators can be adopted to generate unlimited synthetic data, the substantial domain gap between synthetic and real subtomograms hinders its practical utilization. In this w...
Siddhant Bharadwaj, Ashish Vashist, Rashi Singh et al.· 0 citations
The proposed gap is narrower and more defensible than claiming that current models ignore geometry entirely: several systems already respect spherical domain geometry, and emerging work explicitly learns scalar/vector fields on spheres.
GroundBench is introduced, a diagnostic benchmark that separates explanations through six branch-and-merge conditions, each adding a controlled information bundle, and a counterfactual re-ask targeting a real alternate part visible in the same image.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
