Scaling Full Conformal Image Classifiers

2026-09-29

AI Summary

Full conformal prediction remains impractical for large-scale image classification due to prohibitive computational overhead in high-dimensional label spaces. This work proposes a scalable full conformal prediction framework guided by zero-shot vision-language models (VLMs). To overcome computational bottlenecks, it introduces goal-oriented full conformal prediction coupled with a stable online LDA solver. A complete methodological pipeline is further established by integrating lightweight inductive conformal pruning, full conformal prediction, and efficient VLM adaptation techniques. Experimental results demonstrate that the proposed approach substantially reduces test-time computational costs on benchmarks such as ImageNet, yielding efficient prediction sets with more stable coverage rates while rigorously preserving statistical guarantees.

Abstract

Conformal prediction provides set-valued predictions with distribution-free coverage guarantees, making it attractive for high-stakes image classification. However, split conformal prediction is data-inefficient, while full conformal prediction (FCP), despite its stronger statistical efficiency, is computationally prohibitive at scale because it requires candidate-specific model refits at test time. We address this limitation by leveraging zero-shot vision-language models (VLMs) to guide scalable FCP in large label spaces. We introduce Targeted Full Conformal Prediction (T-FCP), which uses a lightweight inductive conformal predictor to prune unlikely labels and applies FCP only to the remaining candidates, reducing computation while retaining the formal guarantee of the combined conformal procedure. We further propose Stabilized Online LDA (SO-LDA), an efficient VLM adaptation solver based on rank-one inverse-covariance updates. Across multiple benchmarks, including ImageNet, T-FCP enables practical full-conformal image classification with modest test-time overhead, yielding efficient prediction sets and more stable empirical coverage than split conformal alternatives.

Problem

• Full Conformal Prediction
• Image Classification
• Computational Scalability
• Conformal Prediction

Innovation

• Full Conformal Prediction
• Vision-Language Models
• Targeted Pruning
• Online LDA
• Conformal Prediction