128 citations · 483 across the 31 of their papers we have counts for
34 papers
Pathwise Information Certificates for Decentralized Adaptive Sensing
Theodoros Tsiligkaridis
We study decentralized adaptive sensing, where multiple agents choose measurements from evolving local beliefs while exchanging information over a communication graph. We ask wheth…
Is Large-Scale Pretraining the Secret to Good Domain Generalization?
Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis +2
Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods co…
The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models
Laura Niss, Kevin Vogt-Lowell, Theodoros Tsiligkaridis
The fine-tuning of large vision-language foundation models remains an underexplored area, particularly regarding its impact on learning gains and catastrophic forgetting. Inspired…
Quantified Task Misalignment to Inform PEFT: An Exploration of Domain Generalization and Catastrophic Forgetting in CLIP
Laura Niss, Kevin Vogt-Lowell, Theodoros Tsiligkaridis
Foundations models are presented as generalists that often perform well over a myriad of tasks. Fine-tuning these models, even on limited data, provides an additional boost in task…
Image-Caption Encoding for Improving Zero-Shot Generalization
Eric Yang Yu, Christopher Liao, Sathvik Ravi +2
Recent advances in vision-language models have combined contrastive approaches with generative methods to achieve state-of-the-art (SOTA) on downstream inference tasks like zero-sh…
Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap
Christopher Liao, Christian So, Theodoros Tsiligkaridis +1
Domain generalization (DG) is an important problem that learns a model which generalizes to unseen test domains leveraging one or more source domains, under the assumption of share…
Robust Fine-Tuning of Vision-Language Models for Domain Generalization
Kevin Vogt-Lowell, Noah Lee, Theodoros Tsiligkaridis +1
Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produ…
Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning
Christopher Liao, Theodoros Tsiligkaridis, Brian Kulis
Over the past year, a large body of multimodal research has emerged around zero-shot evaluation using GPT descriptors. These studies boost the zero-shot accuracy of pretrained VL m…
Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency
Owen Queen, Thomas Hartvigsen, Teddy Koker +3
Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to…
ERM++: An Improved Baseline for Domain Generalization
Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis +2
Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impr…
Domain Adaptation for Time Series Under Feature and Label Shifts
Huan He, Owen Queen, Teddy Koker +3
Unsupervised domain adaptation (UDA) enables the transfer of models trained on source domains to unlabeled target domains. However, transferring complex time series models presents…
Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization
Christopher Liao, Theodoros Tsiligkaridis, Brian Kulis
There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongl…
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency
Xiang Zhang, Ziyuan Zhao, Theodoros Tsiligkaridis +1
Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trend…
Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling
Christopher Liao, Theodoros Tsiligkaridis, Brian Kulis
Domain Adaptation (DA) has received widespread attention from deep learning researchers in recent years because of its potential to improve test accuracy with out-of-distribution l…
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration
Ryan Soklaski, Michael Yee, Theodoros Tsiligkaridis
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability t…
Graph-Guided Network for Irregularly Sampled Multivariate Time Series
Xiang Zhang, Marko Zeman, Theodoros Tsiligkaridis +1
In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with varying time intervals between successive readouts and different subse…
Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration
Theodoros Tsiligkaridis, Athanasios Tsiligkaridis
Deep neural networks achieve high prediction accuracy when the train and test distributions coincide. In practice though, various types of corruptions occur which deviate from this…
Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training
Theodoros Tsiligkaridis, Jay Roberts
Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique that approximately solves a robust optimization…
Ultrasound Diagnosis of COVID-19: Robustness and Explainability
Jay Roberts, Theodoros Tsiligkaridis
Diagnosis of COVID-19 at point of care is vital to the containment of the global pandemic. Point of care ultrasound (POCUS) provides rapid imagery of lungs to detect COVID-19 in pa…
Failure Prediction by Confidence Estimation of Uncertainty-Aware Dirichlet Networks
Theodoros Tsiligkaridis
Reliably assessing model confidence in deep learning and predicting errors likely to be made are key elements in providing safety for model deployment, in particular for applicatio…
Second Order Optimization for Adversarial Robustness and Interpretability
Theodoros Tsiligkaridis, Jay Roberts
Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attac…
Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
Theodoros Tsiligkaridis
Precise estimation of uncertainty in predictions for AI systems is a critical factor in ensuring trust and safety. Deep neural networks trained with a conventional method are prone…
Active query-driven visual search using probabilistic bisection and convolutional neural networks
Athanasios Tsiligkaridis, Theodoros Tsiligkaridis
We present a novel efficient object detection and localization framework based on the probabilistic bisection algorithm. A Convolutional Neural Network (CNN) is trained and used as…
Distributed Optimization of Multi-Beam Directional Communication Networks
Theodoros Tsiligkaridis
We formulate an optimization problem for maximizing the data rate of a common message transmitted from nodes within an airborne network broadcast to a central station receiver whil…