Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation

Forum topic · 小凯 · 2026-04-07

Summary

This paper addresses the under-explored dual-missing scenario in multi-view multi-label classification, where both views and labels are incomplete. Existing methods rely on contrastive learning or information bottleneck theory, but loss-based alignment without explicit structural constraints limits the capture of stable, discriminative shared semantics. The authors propose learning discrete consistent representations through a multi-view shared codebook with cross-view reconstruction, which aligns views within limited codebook embeddings and reduces feature redundancy. At the decision level, a weight estimation method evaluates each view's ability to preserve label correlation structures to improve fused predictions. A fused-teacher self-distillation framework further lets the fused prediction guide view-specific classifiers, feeding global knowledge back into single-view branches to improve generalization under missing labels. Experiments on five benchmark datasets demonstrate effectiveness. Code: https://github.com/xuy11/SCSD.

Paper Overview

Research Area: Computer Vision (CV) Authors: Xu Yan, Jun Yin, Shiliang Sun

Abstract

Although multi-view multi-label learning has been extensively studied, research on the dual-missing scenario, where both views and labels are incomplete, remains largely unexplored. Existing methods mainly rely on contrastive learning or information bottleneck theory to learn consistent representations under missing-view conditions, but loss-based alignment without explicit structural constraints limits the ability to capture stable and discriminative shared semantics.

To address this issue, the authors introduce a more structured mechanism for consistent representation learning: discrete consistent representations are learned through a multi-view shared codebook and cross-view reconstruction, which naturally aligns different views within the limited shared codebook embeddings and reduces feature redundancy.

At the decision level, a weight estimation method evaluates the ability of each view to preserve label correlation structures, assigning weights accordingly to enhance the quality of the fused prediction.

In addition, a fused-teacher self-distillation framework is introduced, where the fused prediction guides the training of view-specific classifiers and feeds global knowledge back into the single-view branches, thereby enhancing the model's generalization ability under missing-label conditions.

The effectiveness of the proposed method is demonstrated through extensive comparative experiments against state-of-the-art methods on five benchmark datasets.

Code

https://github.com/xuy11/SCSD

--- *Auto-collected on 2026-04-07*