7 citations · 10 across the 11 of their papers we have counts for
12 papers
AdaKerNet: Neural Kernel Decoding for Task-Adaptive Prediction with Multimodal Large Models
Konstantinos D. Polyzos, Eleni Oikonomou, Tara Javidi
Large foundation models have been introduced with the promise of efficient adaptation to downstream tasks. Yet, under limited supervision, MLLMs, an important class of large founda…
Enhancing Bayesian Optimization and Active Learning Through Kernel Diversity
Heng Zhang, Haotian Xiang, Konstantinos D. Polyzos +2
Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active learning (AL), as model misspecification can lead to suboptimal performance, whil…
Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
Gerasimos Chatzoudis, Konstantinos D. Polyzos, Zhuowei Li +4
Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used…
3D Scene Rendering with Multimodal Gaussian Splatting
Chi-Shiang Gau, Konstantinos D. Polyzos, Athanasios Bacharis +2
3D scene reconstruction and rendering are core tasks in computer vision, with applications spanning industrial monitoring, robotics, and autonomous driving. Recent advances in 3D G…
A Single Image and Multimodality Is All You Need for Novel View Synthesis
Amirhosein Javadi, Chi-Shiang Gau, Konstantinos D. Polyzos +1
Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular…
BOSfM: A View Planning Framework for Optimal 3D Reconstruction of Agricultural Scenes
Athanasios Bacharis, Konstantinos D. Polyzos, Georgios B. Giannakis +1
Active vision (AV) has been in the spotlight of robotics research due to its emergence in numerous applications including agricultural tasks such as precision crop monitoring and a…
ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting
Konstantinos D. Polyzos, Athanasios Bacharis, Saketh Madhuvarasu +2
Gaussian splatting (GS) along with its extensions and variants provides outstanding performance in real-time scene rendering while meeting reduced storage demands and computational…
3D Reconstruction in Noisy Agricultural Environments: A Bayesian Optimization Perspective for View Planning
Athanasios Bacharis, Konstantinos D. Polyzos, Henry J. Nelson +2
3D reconstruction is a fundamental task in robotics that gained attention due to its major impact in a wide variety of practical settings, including agriculture, underwater, and ur…
Weighted Ensembles for Active Learning with Adaptivity
Konstantinos D. Polyzos, Qin Lu, Georgios B. Giannakis
Labeled data can be expensive to acquire in several application domains, including medical imaging, robotics, and computer vision. To efficiently train machine learning models unde…
Surrogate modeling for Bayesian optimization beyond a single Gaussian process
Qin Lu, Konstantinos D. Polyzos, Bingcong Li +1
Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions emerge in applications as diverse as hype…
Unveiling Anomalous Edges and Nominal Connectivity of Attributed Networks
Konstantinos D. Polyzos, Costas Mavromatis, Vassilis N. Ioannidis +1
Uncovering anomalies in attributed networks has recently gained popularity due to its importance in unveiling outliers and flagging adversarial behavior in a gamut of data and netw…
Real-Time detection, classification and DOA estimation of Unmanned Aerial Vehicle
Konstantinos Polyzos, Evangelos Dermatas
The present work deals with a new passive system for real-time detection, classification and direction of arrival estimator of Unmanned Aerial Vehicles (UAVs). The proposed system…