6 papers
Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification
Daniel Brignac, Fengwei Tian, Banafsheh Latibari +2
Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critical applications such as synthetic aperture radar (SAR) automatic target recogn…
Pay Attention to Where You Looked
Alex Berian, JhihYang Wu, Daniel Brignac +2
Novel view synthesis (NVS) has advanced with generative modeling, enabling photorealistic image generation. In few-shot NVS, where only a few input views are available, existing me…
Is Mamba Reliable for Medical Imaging?
Banafsheh Saber Latibari, Najmeh Nazari, Daniel Brignac +3
State-space models like Mamba offer linear-time sequence processing and low memory, making them attractive for medical imaging. However, their robustness under realistic software a…
CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation
Alex Berian, Daniel Brignac, JhihYang Wu +2
Geospatial imaging leverages data from diverse sensing modalities-such as EO, SAR, and LiDAR, ranging from ground-level drones to satellite views. These heterogeneous inputs offer…
Cascading Unknown Detection with Known Classification for Open Set Recognition
Daniel Brignac, Abhijit Mahalanobis
Deep learners tend to perform well when trained under the closed set assumption but struggle when deployed under open set conditions. This motivates the field of Open Set Recogniti…
Improving Replay Sample Selection and Storage for Less Forgetting in Continual Learning
Daniel Brignac, Niels Lobo, Abhijit Mahalanobis
Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks. One effective…