LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP

1 code implementation • 2 Apr 2024 • Yunshi Huang, Fereshteh Shakeri, Jose Dolz, Malik Boudiaf, Houda Bahig, Ismail Ben Ayed

In this work, we propose and examine from convex-optimization perspectives a generalization of the standard LP baseline, in which the linear classifier weights are learnable functions of the text embedding, with class-wise multipliers blending image and text knowledge.

Efficient Bayes Inference in Neural Networks through Adaptive Importance Sampling

1 code implementation • 3 Oct 2022 • Yunshi Huang, Emilie Chouzenoux, Victor Elvira, Jean-Christophe Pesquet

Bayesian neural networks (BNNs) have received an increased interest in the last years.

Autonomous Driving Decision Making +1

Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution

1 code implementation • 14 Oct 2021 • Yunshi Huang, Emilie Chouzenoux, Jean-Christophe Pesquet

In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution.

Rolling Shutter Correction