1

Combating Missing Modalities in Egocentric Videos at Test Time

We propose a novel online adaptation method that enhances the model's performance under missing modality setting.

Generalizability of Adversarial Robustness Under Distribution Shifts

We propose a benchmark for domain shifts in medical imaging domain.

Evaluation of Test-Time Adaptation Under Computational Time Constraints

We propose a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation.

SimCS: Simulation for Domain Incremental Online Continual Segmentation

We leverage simulated data to mitigate forgetting in domain incremental continual segmentation.

Online Distillation with Continual Learning for Cyclic Domain Shifts

We leverage online distillation for continual semantic segmentation with cyclic domain shifts.

Towards Assessing and Characterizing the Semantic Robustness of Face Recognition

We assess the robustness of face recognition models against semantic variations.

PIVOT: Prompting for Video Continual Learning

We leverage learnable tokens and large-scale pretrained models to mitigate forgetting in video class incremental learning.

Real-Time Evaluation in Online Continual Learning: A New Hope

We leverage learnable tokens and large-scale pretrained models to mitigate forgetting in video class incremental learning.

On the Robustness of Quality Measures for GANs

We assess the adversarial robustness of Inception Score and Frechet Inception Distance (FID) and propose a robustified version of FID.

Certified Robustness in Federated Learning

We assess the certified robustness of models trained in a federated fashion.