Philippe Burlina

---

[home] [about] [research] [recent] [papers] [CV] [other]     

Research focus, sample papers

---

Generative models, Semantic Atttributes, Disentanglement, AI Fairness

Representation learning / Anomaly Detection

RENATA: REpreseNtation And Training Alteration for Bias Mitigation

R'{e} nyi Generative Adversarial Networks

Adversarial ML

Jacks of All Trades, Masters Of None: Addressing Distributional Shift and Obtrusiveness via Transparent Patch Attacks

Random Projections for Adversarial Attack Detection

Zero / Low-Shot Learning

Semantic Zero Shot Learning

Hybrid Hierachical/Semantic Zero-Shot Learning

Hierarchical Classification for Zero-Shot Learning

AI for Medical / Healthcare / Bio

Low-shot deep learning of diabetic retinopathy with potential applications to address artificial intelligence bias in retinal diagnostics and rare ophthalmic diseases

Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics

AI-based detection of erythema migrans and disambiguation against other skin lesions

Deep Reinforcement Learning

DRL/robotic reaching

DRL/robotic grasping

Misc

Video tracking, efficient particle filtering

Probability hypothesis density filters for tracking

Distributed vision sensors, consensus pose estimation

MRCNNs