In a recent, strongly emergent literature on few-shot CLIP adaptation, Linear Probe (LP) has been often reported as a weak baseline. This has motivated intensive research building convoluted prompt learning or feature adaptation strategies. 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. As our objective function depends on two types of variables, i.e., the class visual prototypes and the learnable blending parameters, we propose a computationally efficient block coordinate Majorize-Minimize (MM) descent algorithm. In our full-batch MM optimizer, which we coin LP++, step sizes are implicit, unlike standard gradient descent practices where learning rates are intensively searched over validation sets. By examining the mathematical properties of our loss (e.g., Lipschitz gradient continuity), we build majorizing functions yielding data-driven learning rates and derive approximations of the loss's minima, which provide data-informed initialization of the variables. Our image-language objective function, along with these non-trivial optimization insights and ingredients, yields, surprisingly, highly competitive few-shot CLIP performances. Furthermore, LP++ operates in black-box, relaxes intensive validation searches for the optimization hyper-parameters, and runs orders-of-magnitudes faster than state-of-the-art few-shot CLIP adaptation methods. Our code is available at: \url{https://github.com/FereshteShakeri/FewShot-CLIP-Strong-Baseline.git}.
Bayesian neural networks (BNNs) have received an increased interest in the last years. In BNNs, a complete posterior distribution of the unknown weight and bias parameters of the network is produced during the training stage. This probabilistic estimation offers several advantages with respect to point-wise estimates, in particular, the ability to provide uncertainty quantification when predicting new data. This feature inherent to the Bayesian paradigm, is useful in countless machine learning applications. It is particularly appealing in areas where decision-making has a crucial impact, such as medical healthcare or autonomous driving. The main challenge of BNNs is the computational cost of the training procedure since Bayesian techniques often face a severe curse of dimensionality. Adaptive importance sampling (AIS) is one of the most prominent Monte Carlo methodologies benefiting from sounded convergence guarantees and ease for adaptation. This work aims to show that AIS constitutes a successful approach for designing BNNs. More precisely, we propose a novel algorithm PMCnet that includes an efficient adaptation mechanism, exploiting geometric information on the complex (often multimodal) posterior distribution. Numerical results illustrate the excellent performance and the improved exploration capabilities of the proposed method for both shallow and deep neural networks.
In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel. One of our main contributions is the integration of VBA within a neural network paradigm, following an unrolling methodology. The proposed architecture is trained in a supervised fashion, which allows us to optimally set two key hyperparameters of the VBA model and lead to further improvements in terms of resulting visual quality. Various experiments involving grayscale/color images and diverse kernel shapes, are performed. The numerical examples illustrate the high performance of our approach when compared to state-of-the-art techniques based on optimization, Bayesian estimation, or deep learning.