Related papers: Robustness Analysis on Foundational Segmentation M…

Robust loop closure detection is a critical component of Simultaneous Localization and Mapping (SLAM) algorithms in GNSS-denied environments, such as in the context of planetary exploration. In these settings, visual place recognition often…

Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks. Although several heuristic defenses are proposed to enhance the robustness of federated learning, they do…

Over the recent years, the field of robotics has been undergoing a transformative paradigm shift from fixed, single-task, domain-specific solutions towards adaptive, multi-function, general-purpose agents, capable of operating in complex,…

The dissertation presents four key contributions toward fairness and robustness in vision learning. First, to address the problem of large-scale data requirements, the dissertation presents a novel Fairness Domain Adaptation approach…

Face recognition (FR) has recently made substantial progress and achieved high accuracy on standard benchmarks. However, it has raised security concerns in enormous FR applications because deep CNNs are unusually vulnerable to adversarial…

Machine learning-based embedded systems employed in safety-critical applications such as aerospace and autonomous driving need to be robust against perturbations produced by soft errors. Soft errors are an increasing concern in modern…

Foundation models have transformed natural language processing and computer vision, and their impact is now reshaping remote sensing image analysis. With powerful generalization and transfer learning capabilities, they align naturally with…

In recent years large model trained on huge amount of cross-modality data, which is usually be termed as foundation model, achieves conspicuous accomplishment in many fields, such as image recognition and generation. Though achieving great…

The rapid development of machine learning (ML) and artificial intelligence (AI) applications requires the training of large numbers of models. This growing demand highlights the importance of training models without human supervision, while…

We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on…

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Large-scale pre-trained multimodal transformers, such as ViLBERT and UNITER, have propelled the state of the art in vision-and-language (V+L) research to a new level. Although achieving impressive performance on standard tasks, to date, it…

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world…

Vision Foundation Models (VFMs) have delivered remarkable performance in Domain Generalized Semantic Segmentation (DGSS). However, recent methods often overlook the fact that visual cues are susceptible, whereas the underlying geometry…

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards…

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage. We characterize this stability by their tendency to generate similar outputs…

Computational pathology foundation models (CPathFMs) have emerged as a powerful approach for analyzing histopathological data, leveraging self-supervised learning to extract robust feature representations from unlabeled whole-slide images.…

Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust test-time performance is imperative for most of the…

Image degradations can occur during acquisition, processing, and transmission, altering visual appearance and affecting downstream vision tasks. They are studied in several communities, including synthetic corruption benchmarks for…