cs.LGNov 16, 2026

Learning What the True Labels Would Teach: Posterior Analytic Class-Incremental Learning with Unlabeled Data

Authors: Wei Tang, Tong Wei, Jiahao Zhang, Min-Ling Zhang, Lijie Hu, Fakhri Karray

Organizations: Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Southeast University

Abstract

In class-incremental learning with unlabeled data, each task brings only class names and unlabeled images, so CLIP's zero-shot predictions replace labels. Existing methods train on hard pseudo-labels, but a wrong one gives the true class zero probability, which self-training often confirms. We argue that each image should carry its label posterior, as an analytic classifier trained on posteriors equals the true-label one in expectation. The zero-shot prediction is not this posterior, as its class proportions confound name bias with true imbalance and it ignores other images. We propose Posterior Analytic Class-Incremental Learning (PACIL), which corrects the class prior with a prior selection rule and refines each distribution by a fixed-prior von Mises-Fisher mixture on whitened features. These soft labels train the classifier and replace labels to select its fusion weight with zero-shot CLIP by closed-form leave-one-out cross-validation. We prove that posterior targets minimize the mean-square gap to the true-label prediction and that their argmax widens this gap only through ambiguous images. The fusion weight selected with soft labels loses at most their distance to the posteriors in expected correct decisions. PACIL has the best average incremental accuracy among methods trained without labels on all 18 settings.

Figures & tables

Explore similar work

CardsList
  1. Visual Branch is What You Need for CLIP-based Class-Incremental Learning

    Sep 29, 2026Tao Hu, Zhen-Hao Xie, Jingcai Guo +2Class-Incremental LearningModality Gap in VLMs

  2. In-Context Positive-Unlabeled Learning

    May 7, 2026Siyan Liu, Yi Chang, Manli Cheng +2Binary ClassificationWeakly Supervised Learning

  3. Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning

    May 13, 2026Hao Sun, Zi-Jun Ding, Da-Wei ZhouClass-Incremental LearningVLM Adaptation