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

arXiv: https://arxiv.org/abs/2608.13751 · HTML: https://mlsanity.com/paper/2608.13751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Semantic-Guided Multi-Attention Localization for Zero-Shot Learning](https://mlsanity.com/paper/1903.00502/) (2019)
- [Improving zero-shot learning by mitigating the hubness problem](https://mlsanity.com/paper/1412.6568/) (2014)
- [Ridge Regression, Hubness, and Zero-Shot Learning](https://mlsanity.com/paper/1507.00825/) (2015)
- [Transductive Unbiased Embedding for Zero-Shot Learning](https://mlsanity.com/paper/1803.11320/) (2018)
- [Knowledge-aware Zero-Shot Learning: Survey and Perspective](https://mlsanity.com/paper/2103.00070/) (2021)
- [Generating Visual Representations for Zero-Shot Classification](https://mlsanity.com/paper/1708.06975/) (2017)
- [Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning](https://mlsanity.com/paper/1509.01692/) (2015)
- [VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2203.10444/) (2022)
- [Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP](https://mlsanity.com/paper/2310.00927/) (2023)
- [Whose AI Dream? In search of the aspiration in data annotation](https://mlsanity.com/paper/2203.10748/) (2022)
- [Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification](https://mlsanity.com/paper/1607.08085/) (2016)
- [Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths](https://mlsanity.com/paper/1703.05002/) (2017)
- [Semantically Aligned Bias Reducing Zero Shot Learning](https://mlsanity.com/paper/1904.07659/) (2019)
- [Towards Effective Deep Embedding for Zero-Shot Learning](https://mlsanity.com/paper/1808.10075/) (2018)
- [Image-free Classifier Injection for Zero-Shot Classification](https://mlsanity.com/paper/2308.10599/) (2023)
- [Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition](https://mlsanity.com/paper/1807.09123/) (2018)
- [Alleviating Feature Confusion for Generative Zero-shot Learning](https://mlsanity.com/paper/1909.07615/) (2019)

## Abstract (arXiv)

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 ρu. 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.