CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension

arXiv:2608.13751v1 Announce Type: new Abstract: Large pre-trained models have become foundational components of modern machine learning systems. Yet adapting these models to novel categories typically requires examples from the target distribution. In many domains, however, such data are unavailable. Zero-shot learning (ZSL) permits recognition under these limitations through relying on auxiliary semantic information such as textual descriptions. We introduce CAST (Closed-form Analytic Semantic Transfer), a training-free, image-free framework for extending a pre-trained classifier to previously unseen classes through weight injection. We provide a theoretical foundation for CAST and derive a finite-sample error decomposition that identifies the semantic extrapolation residual rho_u. The residual is a computable, model-agnostic measure and provides a principled criterion for dataset curation and benchmark design. Experiments on standard zero-shot learning benchmarks demonstrate that CAST matches or exceeds existing image-free approaches and approaches the performance of few-shot adaptation methods, while requiring neither iterative optimization nor examples from the target distribution.

Related

• TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
• PERL: Parameter Efficient Reasoning in CLIP Latent Space
• Zero-Shot Retail Theft Detection via Orchestrated Vision Models: A Model-Agnostic, Cost-Effective Alternative to Trained Single-Model Systems
• Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline Study

Source: arXiv cs.CV | 2026-08-17