5 papers
Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
Fair comparison between diffusion-based OOD detectors is challenging, as conclusions can vary with backbone choice, corruption parameterization, and test-time budget. We address th…
GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
Diffusion models learn a time-indexed score field that often inherits approximate equivariances (flips, rotations, circular shifts) from in-distribu…
DopplerGLRTNet for Radar Off-Grid Detection
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
Off-grid targets whose Doppler (or angle) does not lie on the discrete processing grid can severely degrade classical normalized matched-filter (NMF) detectors: even at high SNR, t…
Out-of-Distribution Radar Detection with Complex VAEs: Theory, Whitening, and ANMF Fusion
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
We investigate the detection of weak complex-valued signals immersed in non-Gaussian, range-varying interference, with emphasis on maritime radar scenarios. The proposed methodolog…
Out-of-Distribution Radar Detection in Compound Clutter and Thermal Noise through Variational Autoencoders
Y A Rouzoumka, E Terreaux, C Morisseau +2
This paper presents a novel approach to radar target detection using Variational AutoEncoders (VAEs). Known for their ability to learn complex distributions and identify out-ofdist…