English

PRiSM: Prototype Regularization for Few-Shot VLMs

Computer Vision and Pattern Recognition 2026-07-20 v1

Abstract

Training-free few-shot adaptation methods have gained significant attention recently in the context of Vision-language Models (VLMs). Yet, current benchmarks rely on strong assumptions about the statistics of the adaptation data, e.g., class balance. We question these simplifying assumptions and introduce a more realistic benchmark that varies both the levels of class balance and the effective number of classes in few-shot tasks via Dirichlet sampling. Surprisingly, under our setting, we observe substantial drops in the performances of state-of-the-art methods, more so when the number of labeled samples increases. To mitigate this, we introduce PRiSM, a class-prototype regularization that can be deployed as a plug and play module on top of any existing baseline method, significantly improving performances. Our method optimizes a novel multi-term loss, which includes a regularizer maximizing inter-class pairwise distances, along with additional terms promoting support-feature alignment and fidelity to the baseline prototypes. Furthermore, we introduce an effective and computationally efficient block Majorize-Minimize optimizer for our objective. More specifically, we derive a valid blockwise Lipschitz constant (i.e., a bound on the Hessian's spectral norm), which can be computed efficiently via the Gershgorin circle theorem. Extensive experiments show that PRiSM improves several training-free baselines, with large gains when dealing with severe class imbalance and high numbers of classes.

Cite

@article{arxiv.2607.17820,
  title  = {PRiSM: Prototype Regularization for Few-Shot VLMs},
  author = {Ghassen Baklouti and Omprakash Chakraborty and Jose Dolz and Ismail Ben Ayed},
  journal= {arXiv preprint arXiv:2607.17820},
  year   = {2026}
}

Comments

Submitted to NeurIPS 2026